Domain-independent Features Research Articles

Polarimetric image recovery method with domain-adversarial learning for underwater imaging

Underwater imaging is significant but the images are always subject to degradation, which varies in different underwater environments. Factors such as light scattering, absorption, and environmental noise can affect the quality of underwater images, leading to issues such as color shift, low contrast, and low definition. Polarization information benefits image recovery, and existing learning-based polarimetric imaging methods ignore multiple water types (viewed as domains) and domain generalization. In this paper, we collect, to the best of our knowledge, the richest polarization color image dataset with different water types and present a specially designed neural network UPD-Net firstly employing the domain-adversarial learning strategy to recover the degraded color images. The designed water-type classifier and domain-adversarial learning strategy enable the multi-encoder to output domain-independent features, the decoder outputs clear images consistent with the ground truths with the help of the discriminator and generative-adversarial learning strategy, and there is another decoder responsible for outputting DoLP image. Comparison experiments demonstrate that our method is state-of-the-art in terms of visual effect and value metrics and that it has a strong recovery ability in the source and unseen domains, including in water with high turbidity. The proposed approach has significant potential for underwater imaging and recognition applications in varied underwater environments.

Validation of Deep Learning-based Automatic Retinal Layer Segmentation Algorithms for AMD with Two SD-OCT Devices

PurposeSegmentations of retinal layers in spectral-domain optical coherence tomography (SD-OCT) images serve as a crucial tool for identifying and analyzing the progression of various retinal diseases, encompassing a broad spectrum of abnormalities associated with age-related macular degeneration (AMD). The training of deep-learning algorithms necessitates well-defined ground-truth labels, validated by experts, to delineate boundaries accurately. However, this resource-intensive process has constrained the widespread application of such algorithms across diverse OCT devices. This work validates deep learning image segmentation models across multiple OCT devices by testing robustness in generating clinically relevant metrics. DesignProspective, comparative study. ParticipantsAdults over 50 years of age with no AMD to advanced AMD, as defined in the Age-Related Eye Disease Study (AREDS)), in at least one eye, were enrolled. 402 SD-OCT scans were used in this study. MethodsWe evaluate two separate state-of-the-art segmentation algorithms through a training process using images obtained from one OCT device (Heidelberg-Spectralis) and subsequent testing using images acquired from two OCT devices (Heidelberg-Spectralis and Zeiss-Cirrus). This assessment is performed on a dataset that encompasses a range of retinal pathologies, spanning from disease-free conditions to severe forms of AMD, with a focus on evaluating the device independence of the algorithms. Main Outcome MeasuresPerformance metrics (mean-squared-error, mean-absolute-error, dice-coefficients) for the segmentations of the internal limiting membrane (ILM), retinal-pigment-epithelium (RPE), and RPE to Bruch’s-membrane (BM) region, along with en face thickness maps, volumetric estimations (in mm3). Violin plots and Bland-Altman plots comparing predictions against ground-truth are also presented. ResultsThe UNet and DeepLabv3, trained on Spectralis B-scans, demonstrate clinically useful outcomes when applied to Cirrus test B-scans. Review of the Cirrus test-data by two independent annotators revealed that the aggregated-mean-absolute-error in pixels for ILM was 1.82±0.24 (equivalent to 7.0±0.9 μm) and for RPE was 2.46±0.66 (9.5±2.6 μm). Additionally, the dice-similarity-coefficient for the RPE-drusen complex (RPE-DC) region, comparing predictions to ground truth, reached 0.87±0.01. ConclusionIn the pursuit of task-specific goals such as retinal layer segmentation, a segmentation network has the capacity to acquire domain-independent features from a large training dataset. This enables the utilization of the network to execute tasks in domains where ground truth is hard to generate.

Progressive Unsupervised Domain Adaptation for Radio Frequency Signal Attribute Recognition across Communication Scenarios

As the development of low-altitude economies and aerial countermeasures continues, the safety of unmanned aerial vehicles becomes increasingly critical, making emitter identification in remote sensing practices more essential. Effective recognition of radio frequency (RF) signal attributes is a prerequisite for identifying emitters. However, due to diverse wireless communication environments, RF signals often face challenges from complex and time-varying wireless channel conditions. These challenges lead to difficulties in data collection and annotation, as well as disparities in data distribution across different communication scenarios. To address this issue, this paper proposes a progressive maximum similarity-based unsupervised domain adaptation (PMS-UDA) method for RF signal attribute recognition. First, we introduce a noise perturbation consistency optimization method to enhance the robustness of the PMS-UDA method under low signal-to-noise conditions. Subsequently, a progressive label alignment training method is proposed, combining sample-level maximum correlation with distribution-level maximum similarity optimization techniques to enhance the similarity of cross-domain features. Finally, a domain adversarial optimization method is employed to extract domain-independent features, reducing the impact of channel scenarios. The experimental results demonstrate that the PMS-UDA method achieves superior recognition performance in automatic modulation recognition and RF fingerprint identification tasks, as well as across both ground-to-ground and air-to-ground scenarios, compared to baseline methods.

RetVes segmentation: A pseudo-labeling and feature knowledge distillation optimization technique for retinal vessel channel enhancement

Recent advancements in retinal vessel segmentation, which employ transformer-based and domain-adaptive approaches, show promise in addressing the complexity of ocular diseases such as diabetic retinopathy. However, current algorithms face challenges in effectively accommodating domain-specific variations and limitations of training datasets, which fail to represent real-world conditions comprehensively. Manual inspection by specialists remains time-consuming despite technological progress in medical imaging, underscoring the pressing need for automated and robust segmentation techniques. Additionally, these methods have deficiencies in handling unlabeled target sets, requiring extra preprocessing steps and manual intervention, which hinders their scalability and practical application in clinical settings. This research introduces a novel framework that employs semi-supervised domain adaptation and contrastive pre-training to address these limitations. The proposed model effectively learns from target data by implementing a novel pseudo-labeling approach and feature-based knowledge distillation within a temporal convolutional network (TCN) and extracts robust, domain-independent features. This approach enhances cross-domain adaptation, significantly enhancing the model's versatility and performance in clinical settings. The semi-supervised domain adaptation component overcomes the challenges posed by domain shifts, while pseudo-labeling utilizes the data's inherent structure for enhanced learning, which is particularly beneficial when labeled data is scarce. Evaluated on the DRIVE and CHASE_DB1 datasets, which contain clinical fundus images, the proposed model achieves outstanding performance, with accuracy, sensitivity, specificity, and AUC values of 0.9792, 0.8640, 0.9901, and 0.9868 on DRIVE, and 0.9830, 0.9058, 0.9888, and 0.9950 on CHASE_DB1, respectively, outperforming current state-of-the-art vessel segmentation methods. The partitioning of datasets into training and testing sets ensures thorough validation, while extensive ablation studies with thorough sensitivity analysis of the model's parameters and different percentages of labeled data further validate its robustness.

Latent-SDE: guiding stochastic differential equations in latent space for unpaired image-to-image translation

Score-based diffusion models have shown promising results in unpaired image-to-image translation (I2I). However, the existing methods only perform unpaired I2I in pixel space, which requires high computation costs. To this end, we propose guiding stochastic differential equations in latent space (Latent-SDE) that extracts domain-specific and domain-independent features of the image in the latent space to calculate the loss and guides the inference process of a pretrained SDE in the latent space for unpaired I2I. To refine the image in the latent space, we propose a latent time-travel strategy that increases the sampling timestep. Empirically, we compare Latent-SDE to the baseline of the score-based diffusion model on three widely adopted unpaired I2I tasks under two metrics. Latent-SDE achieves state-of-the-art on Cat →\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\rightarrow $$\\end{document} Dog and is competitive on the other two tasks. Our code will be freely available for public use upon acceptance at https://github.com/zhangXJ147/Latent-SDE.

Meta-learning based infrared ship object detection model for generalization to unknown domains

Infrared images exhibit considerable variations in probability distributions, stemming from the utilization of distinct infrared sensors and the influence of diverse environmental conditions. The variations pose great challenges for deep learning models to detect ship objects and adapt to unseen maritime environments. To address the domain shift problem, we propose an end-to-end infrared ship object detection model based on meta-learning neural network to improve domain adaptation for target domain where data is not available at training phase. Different from existing domain generalization methods, the novelty of our model lies in the effective exploitation of meta-learning and domain adaptation, ensuring that the extracted domain-independent features are meaningful and domain-invariant at the semantic level. Firstly, a double gradient-based meta-learning algorithm is designed to solve the common optimal descent direction between different domains through two gradient updates in the inner and outer loops. The algorithm enables extraction of domain-invariant features from the pseudo-source and pseudo-target domain data. Secondly, a domain discriminator with dynamic-weighted gradient reversal layer (DWGRL) is designed to accurately classify domain-invariant features and provide additional global supervision information. Finally, a multi-scale feature aggregation method is proposed to improve the extraction of multi-scale domain-invariant features. It can effectively fuse local features at different scales and global features of targets. Extensive experimental results conducted in real nighttime water surface scenes demonstrate that the proposed model achieves very high detection accuracy on target domain data, even no target domain data was used during the training phase. Compared to the existing methods, our method not only improves the detection accuracy of infrared ships by 18%, but also exhibits the smallest standard deviation with a value of 0.93, indicating its superior generalization performance.

Semi-physical simulation-driven contrastive decoupling net for intelligent fault diagnosis of unseen machines under varying speed

Multi-source domain generalization provides a good idea for intelligent fault diagnosis of unseen machines. However, the acquisition of multi-source training sets would not only affect the generalization effect, but also cause huge economic loss. Too much difference between source training sets would lead to negative transfer, while too much similarity between the sets would cause zero transfer. Simultaneously, the current methods based on the assumption of stable speed cannot realize intelligent diagnosis under varying speed. Therefore, a semi-physical simulation-driven contrastive decoupling network is presented. First, a phenomenological model is used to generate large amount of simulation data with different modulation frequencies and signal-to-noise ratios to provide support for the training of the net. Next, with the joint help of simulation data and physical data, a contrastive framework is introduced to extract domain-independent features. Finally, a decoupling framework is proposed to minimize speed-related information while maximizing health-related features, thereby enabling intelligent diagnosis of unseen devices at varying speed. The proposed method is tested on two cases operating under sharp speed variation and compared with some state-of-the-art methods. The results show the superiority of the proposed net in intelligent diagnosis of unseen equipment under drastically varying speed.

Energy-guided diffusion model for CBCT-to-CT synthesis

Cone Beam Computed Tomography (CBCT) plays a crucial role in Image-Guided Radiation Therapy (IGRT), providing essential assurance of accuracy in radiation treatment by monitoring changes in anatomical structures during the treatment process. However, CBCT images often face interference from scatter noise and artifacts, posing a significant challenge when relying solely on CBCT for precise dose calculation and accurate tissue localization. There is an urgent need to enhance the quality of CBCT images, enabling a more practical application in IGRT. This study introduces EGDiff, a novel framework based on the diffusion model, designed to address the challenges posed by scatter noise and artifacts in CBCT images. In our approach, we employ a forward diffusion process by adding Gaussian noise to CT images, followed by a reverse denoising process using ResUNet with an attention mechanism to predict noise intensity, ultimately synthesizing CBCT-to-CT images. Additionally, we design an energy-guided function to retain domain-independent features and discard domain-specific features during the denoising process, enhancing the effectiveness of CBCT-CT generation. We conduct numerous experiments on the thorax dataset and pancreas dataset. The results demonstrate that EGDiff performs better on the thoracic tumor dataset with SSIM of 0.850, MAE of 26.87 HU, PSNR of 19.83 dB, and NCC of 0.874. EGDiff outperforms SoTA CBCT-to-CT synthesis methods on the pancreas dataset with SSIM of 0.754, MAE of 32.19 HU, PSNR of 19.35 dB, and NCC of 0.846. By improving the accuracy and reliability of CBCT images, EGDiff can enhance the precision of radiation therapy, minimize radiation exposure to healthy tissues, and ultimately contribute to more effective and personalized cancer treatment strategies.

Multi-Scale Similarity Guidance Few-Shot Network for Ship Segmentation in SAR Images

Target detection and segmentation in synthetic aperture radar (SAR) images are vital steps for many remote sensing applications. In the era of data-driven deep learning, this task is extremely challenging due to the limited labeled data. Few-shot learning has the ability to learn quickly from a few samples with supervised information. Inspired by this, a few-shot learning framework named MSG-FN is proposed to solve the segmentation of ship targets in heterologous SAR images with few annotated samples. The proposed MSG-FN adopts a dual-branch network consisting of a support branch and a query branch. The support branch is used to extract features with an encoder, and the query branch uses a U-shaped encoder–decoder structure to segment the target in the query image. The encoder of each branch is composed of well-designed residual blocks combined with filter response normalization to capture robust and domain-independent features. A multi-scale similarity guidance module is proposed to improve the scale adaptability of detection by applying hand-on-hand guidance of support features to query features of various scales. In addition, a SAR dataset named SARShip-4i is built to evaluate the proposed MSG-FN, and the experimental results show that the proposed method achieves superior segmentation results compared with the state-of-the-art.

Improved Feature Representation Using Collaborative Network for Cross-Domain Sentiment Analysis

Sentiment Analysis task helps us to estimate the opinion of a person from his reviews or comments about a product, person, politics, etc., Cross-Domain Sentiment Analysis (CDSA) empowers the Sentiment models with the ability to forecast the opinion of a review coming from a different domain other than the domain where the model is trained. The challenge of the CDSA model relies on bridging the relationship between words in the source and target domain. Several types of research in CDSA focus on determining the domain invariant features to adapt the model to the target domain, such model shows less focus on aspect terms of the sentence. We propose CWAN (Collaborative Word Attention Network), which integrates aspects and domain invariant features of the sentences to calculate the sentiment. CWAN uses attention networks to capture the domain-independent features and aspects of the sentences. The sentence and aspect attention models are executed collaboratively to determine the sentiment of the sentence. Amazon product review dataset is used in this experiment. The performance of the CWAN model is compared with other baseline CDSA models. The results show that CWAN outperforms other baseline models.

A Resource-Efficient Cross-Domain Sensing Method for Device-Free Gesture Recognition With Federated Transfer Learning

Emerging Wi-Fi sensing technologies and applications make indoor ubiquitous sensing possible. Deep learning empowered Wi-Fi sensing model enables detection, recognition automatically, without being explicitly programmed. Due to indoor sensing privacy and ubiquitous sensing ability concerns, it is absolutely necessary to conduct in-depth research on Wi-Fi sensing security training and cross-domain sensing issues. To address them, in this paper, we propose to learn domain independent features, distributed model training and localized inference based on federated transfer learning. Moreover, several efficient methods are proposed to provide a distributed edge Wi-Fi sensing scheme with sensing data privacy protection, costing less time, communication, computing and energy resources. We implement the proposed framework and conduct experiments with Widar3.0 datasets to evaluate its performance. The results demonstrate that our framework performs better for cross-domain Wi-Fi sensing while preserving user data privacy and saving resources.

Local Correlation Ensemble with GCN Based on Attention Features for Cross-domain Person Re-ID

Person re-identification (Re-ID) has achieved great success in single-domain. However, it remains a challenging task to adapt a Re-ID model trained on one dataset to another one. Unsupervised domain adaption (UDA) was proposed to migrate a model from a labeled source domain to an unlabeled target domain. The main difference in the cross-domain is different background styles. Although the style transfer approach effectively reduces inter-domain gaps, it ignores the reduction of intra-class differences. Clustering-based pipelines maintain state-of-the-art performance for UDA by learning domain-independent features; however, most existing models do not sufficiently exploit the rich unlabeled samples in target domains due to unsatisfactory clustering. Thus, we propose a novel local correlation ensemble model that focuses on the diversity of intra-class information and the reliability of class centers. Specifically, a pedestrian attention module is proposed to enable the encoder to pay more attention to the person’s features to relieve interference caused by the shared background style. Furthermore, we propose a priority-distance graph convolutional network (PDGCN) module that employs a graph convolutional network network to predict the priority of a node as a class center and then calculates the distance between nodes with high priority values to screen out the class center nodes. Finally, the encoder features (local) and PDGCN features (context-aware) are combined to perform person Re-ID. The results of experiments on the large-scale public Re-ID datasets verified the effectiveness of the proposed method.

Cross‐domain sentiment classification using decoding‐enhanced bidirectional encoder representations from transformers with disentangled attention

SummaryCross‐domain sentiment classification is a significant task of sentiment analysis that objectives to predict the opinion orientation of text documents in the target domain by using the source domain's learned classifier. Most of the existing approaches of domain‐adaptation in sentiment classification focus on sharing low‐dimensional features across the domain using domain independent and specific features to mitigate the gap between domains. Earlier cross‐domain sentiment classification approaches mainly focused on document level and sentence level, they cannot consider the full impact of aspect words, position of the words, and long‐term dependencies. To address this concern, we propose a model for cross‐domain sentiment classification, which is based on decoding‐enhanced BERT with disentangled attention (DeBERTa). DeBERTa is a pretrained language model based on transformer architecture. In this article, we perform sentence and aspect embedding to mine wordpiece information from text document. DeBERTa language‐model utilize disentangled attention mechanism and an enhanced mask decoder to understand the expression features. Disentangled attention mechanism is used to encode each word into two vectors (i.e., content and position vector). In order to predict the masked tokens during model pretraining, an enhanced mask decoder is employed, which incorporates absolute positions in the decoding layer. Finally, experiments are conducted on the benchmark dataset that demonstrates the superiority of fine‐tuned DeBERTa model for cross‐domain sentiment classification tasks.

HandGest: Hierarchical Sensing for Robust-in-the-Air Handwriting Recognition With Commodity WiFi Devices

Recent advances in wireless sensing techniques have made it possible to recognize hand gestures using channel state information (CSI) in commodity WiFi devices. Existing WiFi-based gesture recognition systems mainly use learning-based pattern recognition methods to recognize different gestures, however, these methods fail to work well when the locations of transceivers, the relative location and orientation of the hand with respect to transceivers, and/or the hand gesturing size change, leading to inconsistent signal patterns caused by those factors. Although some recent efforts have been made to address the so-called “domain-dependent” gesture recognition problem, they either require prior knowledge on initial locations of the hand and WiFi devices or need to train several classifiers for the specific domains. Different from the state-of-the-art methods, we construct two distinct features from a hand-oriented view (rather than from a transceiver’s view), namely, the dynamic phase vector (DPV) and motion rotation variable (MRV), which are quite consistent in characterizing a big set of handwriting gestures, despite significant change in locations of transceivers, the relative location and orientation of the hand with respect to transceivers, and the drawing sizes. We further incorporate a hierarchical sensing framework and develop HandGest—a real-time handwriting gesture recognition system using commodity WiFi devices, to precisely recognize a great number of “in-the-air” handwritings based on the aforementioned two domain-independent features and a pipeline of specific features. Extensive experiments have been done in practical settings with 20 volunteers, evaluation results demonstrate that HandGest outperforms state-of-the-art methods on a large number of handwritings with different transceivers’ location, different initial hand locations and orientations, as well as different drawing sizes. Given its superior performance, we believe that HandGest paves a new way to enhance the real-world practicality of WiFi-based gesture recognition.

WiGRUNT: WiFi-Enabled Gesture Recognition Using Dual-Attention Network

Gestures constitute an important form of nonverbal communication where bodily actions are used for delivering messages alone or in parallel with spoken words. Recently, there exists an emerging trend of WiFi sensing-enabled gesture recognition due to its inherent merits like remote sensing, non-line-of-sight covering, and privacy-friendly. However, current WiFi-based approaches mainly reply on domain-specific training since they don’t know “where to look” and “when to look.” To this end, we propose WiGRUNT, a WiFi-enabled gesture recognition system using dual-attention network, to mimic how a keen human being intercepting a gesture regardless of the environment variations. The key insight is to train the network to dynamically focus on the domain-independent features of a gesture on the WiFi channel state information via a spatial-temporal dual-attention mechanism. WiGRUNT roots in a deep residual network (ResNet) backbone to evaluate the importance of spatial-temporal clues and exploit their inbuilt sequential correlations for fine-grained gesture recognition. We evaluate WiGRUNT on the open Widar3 dataset and show that it significantly outperforms its state-of-the-art rivals by achieving the best-ever performance in-domain or cross-domain.

WiFi-Based Cross-Domain Gesture Recognition via Modified Prototypical Networks

Numerous deep learning studies have achieved remarkable advances in WiFi-based human gesture recognition (HGR) using channel state information (CSI). However, since the CSI patterns of the same gesture change across domains (i.e., users, environments, locations, and orientations), recognition accuracy might degrade significantly when applying the trained model to new domains. To overcome this problem, we propose a WiFi-based cross-domain gesture recognition system (WiGr) which has a domain-transferable mapping to construct an embedding space where the representations of samples from the same class are clustered, and those from different classes are separated. The key insight of WiGr is using the similarity between the query sample representation and the class prototypes in the embedding space to perform the gesture classification, which can avoid the influence of the cross-domain CSI patterns change. Meanwhile, we present a dual-path prototypical network (Dual-Path PN) which consists of a deep feature extractor and a dual-path (i.e., Path-A and Path-B substructures) recognizer. The trained feature extractor can extract the gesture-related domain-independent features from CSI, namely, the domain-transferable mapping. In addition, WiGr implements the cross-domain HGR based on only a pair of WiFi devices without retraining in the new domain. We conduct comprehensive experiments on three data sets, one is built by ourselves and the others are public data sets. The evaluation suggests that WiGr achieves 86.8%–92.7% in-domain recognition accuracy and 83.5%–93% cross-domain accuracy under the four-shot condition.

A Privacy-Preserving Cross-Domain Healthcare Wearables Recommendation Algorithm Based on Domain-Dependent and Domain-Independent Feature Fusion.

Recently, recommender systems are applied to provide personalized recomendation for healthcare wearables. However, due to the sparsity problem, traditional recommendation algorithms are difficult to achieve desired performance. Considering that consumers often buy and rate other types of items on E-commerce platforms, we can leverage significant information in the auxiliary domains to improve the recommendation performance of healthcare wearables, which can be regarded as cross-domain recommendation. However, traditional cross-domain recommendation model cannot fully represent user's characteristics and fail to consider the leaks of original auxiliary domain ratings during the information transfer process. To overcome the two shortcomings, this paper proposes a Privacy-Preserving Cross-Domain Healthcare Wearables Recommendation algorithm (PPCDHWRec). Firstly, user's characteristics are divided into domain-dependent features and domain-independent features, which complement each other and fully depict the user's characteristics. Secondly, inspired by the latent factor model, we factorize the original rating information of each auxiliary domain by Funk-SVD and Orthogonal Nonnegative Matrix Tri-Factorization (ONMTF) model, to obtain user's domain-dependent and domain-independent features, respectively. Finally, the Factorization Machine algorithm is used to fuse the obtained user's features with the target domain information to provide the recommendation results. By hiding the item latent factors obtained in the factorization process, PPCDHWRec ensures that the original information cannot be inferred from the transferred user hidden vector. Hence, PPCDHWRec is a privacy-preserving recommendation model. Experiments on two groups of auxiliary domains, having high and low correlations with target domain, show the effectiveness of PPCDHWRec.

Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translation.

Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs). However, existing approaches are mostly designed in an unsupervised manner, while little attention has been paid to domain information within unpaired data. In this article, we treat domain information as explicit supervision and design an unpaired image-to-image translation framework, Domain-supervised GAN (DosGAN), which takes the first step towards the exploration of explicit domain supervision. In contrast to representing domain characteristics using different generators or domain codes, we pre-train a classification network to explicitly classify the domain of an image. After pre-training, this network is used to extract the domain-specific features of each image. Such features, together with the domain-independent features extracted by another encoder (shared across different domains), are used to generate image in target domain. Extensive experiments on multiple facial attribute translation, multiple identity translation, multiple season translation and conditional edges-to-shoes/handbags demonstrate the effectiveness of our method. In addition, we can transfer the domain-specific feature extractor obtained on the Facescrub dataset with domain supervision information to unseen domains, such as faces in the CelebA dataset. We also succeed in achieving conditional translation with any two images in CelebA, while previous models like StarGAN cannot handle this task.

Towards fully domain‐independent gesture recognition using COTS WiFi device

This letter proposes a fully domain-independent WiFi-based gesture recognition system based on the multi-label adversarial network. Unlike pioneer machine learning works, our system does not require retraining in the target domain, which benefits from our key idea of eliminating fully domain information such as orientations, locations, environment information. The system proposed by us includes three parts: Feature extractor, domain discriminator, and gesture recogniser. The feature extractor attempts to deceive the domain discriminator based on the adversarial network structure so that it is difficult to judge the input domain label, thereby obtaining domain-independent features and realising fully domain-independent gesture recognition. Extensive experiments are conducted on the Widar 3.0 dataset and our dataset to evaluate system performance. The results show that our system can achieve an in-domain recognition accuracy of 93.2% and a cross-domain recognition accuracy of 87.1%, which is superior to other state-of-the-art works.

Widar3.0: Zero-Effort Cross-Domain Gesture Recognition With Wi-Fi.

With the development of signal processing technology, the ubiquitous Wi-Fi devices open an unprecedented opportunity to solve the challenging human gesture recognition problem by learning motion representations from wireless signals. Wi-Fi-based gesture recognition systems, although yield good performance on specific data domains, are still practically difficult to be used without explicit adaptation efforts to new domains. Various pioneering approaches have been proposed to resolve this contradiction but extra training efforts are still necessary for either data collection or model re-training when new data domains appear. To advance cross-domain recognition and achieve fully zero-effort recognition, we propose Widar3.0, a Wi-Fi-based zero-effort cross-domain gesture recognition system. The key insight of Widar3.0 is to derive and extract domain-independent features of human gestures at the lower signal level, which represent unique kinetic characteristics of gestures and are irrespective of domains. On this basis, we develop a one-fits-all general model that requires only one-time training but can adapt to different data domains. Experiments on various domain factors (i.e. environments, locations, and orientations of persons) demonstrate the accuracy of 92.7% for in-domain recognition and 82.6%-92.4% for cross-domain recognition without model re-training, outperforming the state-of-the-art solutions.