Visual Feature Space Research Articles

Action similarity warps visual feature space in working memory

Visual working memory (VWM) retains representations of past visual information for future action. Yet to date, most studies have approached VWM as just serving perception beyond the immediate. Whether and how prospective actions shape information in VWM remains largely unknown, in part because typical experimental setups limit behavior to simple button presses. In two experiments (one preregistered), using a novel interactive VWM task, we show that the similarity of the actions that we intend to perform on memory items adaptively distorts their representation. Participants memorized the orientation of two bars, after which they were informed as to which manual actions they should reproduce these orientations with in a memory recall test. We observed that perceptually similar items were remembered as more distinct when paired with different action plans versus the same action plan. A control experiment showed that this action-induced effect reflects a true change in the visual representation rather than a motor bias. These findings demonstrate that VWM representations are flexibly adapted to guide specific overt actions and provide evidence that action plans can retrospectively warp sensory feature space in VWM.

Reliable object tracking by multimodal hybrid feature extraction and transformer-based fusion

Visual object tracking, which is primarily based on visible light image sequences, encounters numerous challenges in complicated scenarios, such as low light conditions, high dynamic ranges, and background clutter. To address these challenges, incorporating the advantages of multiple visual modalities is a promising solution for achieving reliable object tracking. However, the existing approaches usually integrate multimodal inputs through adaptive local feature interactions, which cannot leverage the full potential of visual cues, thus resulting in insufficient feature modeling. In this study, we propose a novel multimodal hybrid tracker (MMHT) that utilizes frame-event-based data for reliable single object tracking. The MMHT model employs a hybrid backbone consisting of an artificial neural network (ANN) and a spiking neural network (SNN) to extract dominant features from different visual modalities and then uses a unified encoder to align the features across different domains. Moreover, we propose an enhanced transformer-based module to fuse multimodal features using attention mechanisms. With these methods, the MMHT model can effectively construct a multiscale and multidimensional visual feature space and achieve discriminative feature modeling. Extensive experiments demonstrate that the MMHT model exhibits competitive performance in comparison with that of other state-of-the-art methods. Overall, our results highlight the effectiveness of the MMHT model in terms of addressing the challenges faced in visual object tracking tasks.

Perceptual similarity judgments do not predict the distribution of errors in working memory.

Population coding models provide a quantitative account of visual working memory (VWM) retrieval errors with a plausible link to the response characteristics of sensory neurons. Recent work has provided an important new perspective linking population coding to variables of signal detection, including d-prime, and put forward a new hypothesis: that the distribution of recall errors on, for example, a color wheel, is a consequence of the psychological similarity between points in that stimulus space, such that the exponential-like psychophysical distance scaling function can fulfil the role of population tuning and obviate the need to fit a tuning width parameter to recall data. Using four different visual feature spaces, we measured psychophysical similarity and memory errors in the same participants. Our results revealed strong evidence for a common source of variability affecting similarity judgments and recall estimates but did not support any consistent relationship between psychophysical similarity functions and VWM errors. At the group level, the responsiveness functions obtained from the psychophysical similarity task diverged strongly from those that provided the best fit to working memory errors. At the individual level, we found convincing evidence against an association between observed and best-fitting similarity functions. Finally, our results show that the newly proposed exponential-like responsiveness function has in general no advantage over the canonical von Mises (circular normal) function assumed by previous population coding models. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Visual Hallucination Elevates Speech Recognition

Due to the detrimental impact of noise on the conventional audio speech recognition (ASR) task, audio-visual speech recognition~(AVSR) has been proposed by incorporating both audio and visual video signals. Although existing methods have demonstrated that the aligned visual input of lip movements can enhance the robustness of AVSR systems against noise, the paired videos are not always available during inference, leading to the problem of the missing visual modality, which restricts their practicality in real-world scenarios. To tackle this problem, we propose a Discrete Feature based Visual Generative Model (DFVGM) which exploits semantic correspondences between the audio and visual modalities during training, generating visual hallucinations in lieu of real videos during inference. To achieve that, the primary challenge is to generate the visual hallucination given the noisy audio while preserving semantic correspondences with the clean speech. To tackle this challenge, we start with training the audio encoder in the Audio-Only (AO) setting, which generates continuous semantic features closely associated with the linguistic information. Simultaneously, the visual encoder is trained in the Visual-Only (VO) setting, producing visual features that are phonetically related. Next, we employ K-means to discretize the continuous audio and visual feature spaces. The discretization step allows DFVGM to capture high-level semantic structures that are more resilient to noise and generate visual hallucinations with high quality. To evaluate the effectiveness and robustness of our approach, we conduct extensive experiments on two publicly available datasets. The results demonstrate that our method achieves a remarkable 53% relative reduction (30.5%->12.9%) in Word Error Rate (WER) on average compared to the current state-of-the-art Audio-Only (AO) baselines while maintaining comparable results (< 5% difference) under the Audio-Visual (AV) setting even without video as input.

Cross-Modal Match for Language Conditioned 3D Object Grounding

Language conditioned 3D object grounding aims to find the object within the 3D scene mentioned by natural language descriptions, which mainly depends on the matching between visual and natural language. Considerable improvement in grounding performance is achieved by improving the multimodal fusion mechanism or bridging the gap between detection and matching. However, several mismatches are ignored, i.e., mismatch in local visual representation and global sentence representation, and mismatch in visual space and corresponding label word space. In this paper, we propose crossmodal match for 3D grounding from mitigating these mismatches perspective. Specifically, to match local visual features with the global description sentence, we propose BEV (Bird’s-eye-view) based global information embedding module. It projects multiple object proposal features into the BEV and the relations of different objects are accessed by the visual transformer which can model both positions and features with long-range dependencies. To circumvent the mismatch in feature spaces of different modalities, we propose crossmodal consistency learning. It performs cross-modal consistency constraints to convert the visual feature space into the label word feature space resulting in easier matching. Besides, we introduce label distillation loss and global distillation loss to drive these matches learning in a distillation way. We evaluate our method in mainstream evaluation settings on three datasets, and the results demonstrate the effectiveness of the proposed method.

Zero-Shot Learning With Attentive Region Embedding and Enhanced Semantics.

The performance of zero-shot learning (ZSL) can be improved progressively by learning better features and generating pseudosamples for unseen classes. Existing ZSL works typically learn feature extractors and generators independently, which may shift the unseen samples away from their real distribution and suffers from the domain bias problem. In this article, to tackle this challenge, we propose a variational autoencoder (VAE)-based framework, that is, joint Attentive Region Embedding with Enhanced Semantics (AREES), which is tailored to advance the zero-shot recognition. Specifically, AREES is end-to-end trainable and consists of three network branches: 1) attentive region embedding is used to learn the semantic-guided visual features by the attention mechanism (AM); 2) a decomposition structure and a semantic pivot regularization are used to extract enhanced semantics; and 3) a multimodal VAE (mVAE) with the cross-reconstruction loss and the distribution alignment loss is used to obtain a shared latent embedding space of visual features and semantics. Finally, features' extraction and features' generation are optimized together in AREES to address the domain shift problem to a large extent. The comprehensive evaluations on six benchmarks, including the ImageNet, demonstrate the superiority of the proposed model over its state-of-the-art counterparts.

Semantics-Guided Contrastive Network for Zero-Shot Object Detection.

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the available semantic information on unseen classes, which can easily bias towards the seen categories; 2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth label and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks.

High-dimensional topographic organization of visual features in the primate temporal lobe

The inferotemporal cortex supports our supreme object recognition ability. Numerous studies have been conducted to elucidate the functional organization of this brain area, but there are still important questions that remain unanswered, including how this organization differs between humans and non-human primates. Here, we use deep neural networks trained on object categorization to construct a 25-dimensional space of visual features, and systematically measure the spatial organization of feature preference in both male monkey brains and human brains using fMRI. These feature maps allow us to predict the selectivity of a previously unknown region in monkey brains, which is corroborated by additional fMRI and electrophysiology experiments. These maps also enable quantitative analyses of the topographic organization of the temporal lobe, demonstrating the existence of a pair of orthogonal gradients that differ in spatial scale and revealing significant differences in the functional organization of high-level visual areas between monkey and human brains.

Brain-guided manifold transferring to improve the performance of spiking neural networks in image classification.

Spiking neural networks (SNNs), as the third generation of neural networks, are based on biological models of human brain neurons. In this work, a shallow SNN plays the role of an explicit image decoder in the image classification. An LSTM-based EEG encoder is used to construct the EEG-based feature space, which is a discriminative space in viewpoint of classification accuracy by SVM. Then, the visual feature vectors extracted from SNN is mapped to the EEG-based discriminative features space by manifold transferring based on mutual k-Nearest Neighbors (Mk-NN MT). This proposed "Brain-guided system" improves the separability of the SNN-based visual feature space. In the test phase, the spike patterns extracted by SNN from the input image is mapped to LSTM-based EEG feature space, and then classified without need for the EEG signals. The SNN-based image encoder is trained by the conversion method and the results are evaluated and compared with other training methods on the challenging small ImageNet-EEG dataset. Experimental results show that the proposed transferring the manifold of the SNN-based feature space to LSTM-based EEG feature space leads to 14.25% improvement at most in the accuracy of image classification. Thus, embedding SNN in the brain-guided system which is trained on a small set, improves its performance in image classification.

Zero-Shot Neural Decoding with Semi-Supervised Multi-View Embedding.

Zero-shot neural decoding aims to decode image categories, which were not previously trained, from functional magnetic resonance imaging (fMRI) activity evoked when a person views images. However, having insufficient training data due to the difficulty in collecting fMRI data causes poor generalization capability. Thus, models suffer from the projection domain shift problem when novel target categories are decoded. In this paper, we propose a zero-shot neural decoding approach with semi-supervised multi-view embedding. We introduce the semi-supervised approach that utilizes additional images related to the target categories without fMRI activity patterns. Furthermore, we project fMRI activity patterns into a multi-view embedding space, i.e., visual and semantic feature spaces of viewed images to effectively exploit the complementary information. We define several source and target groups whose image categories are very different and verify the zero-shot neural decoding performance. The experimental results demonstrate that the proposed approach rectifies the projection domain shift problem and outperforms existing methods.

Explainable CAD System for Classification of Acute Lymphoblastic Leukemia Based on a Robust White Blood Cell Segmentation

Leukemia is a significant health challenge, with high incidence and mortality rates. Computer-aided diagnosis (CAD) has emerged as a promising approach. However, deep-learning methods suffer from the “black box problem”, leading to unreliable diagnoses. This research proposes an Explainable AI (XAI) Leukemia classification method that addresses this issue by incorporating a robust White Blood Cell (WBC) nuclei segmentation as a hard attention mechanism. The segmentation of WBC is achieved by combining image processing and U-Net techniques, resulting in improved overall performance. The segmented images are fed into modified ResNet-50 models, where the MLP classifier, activation functions, and training scheme have been tested for leukemia subtype classification. Additionally, we add visual explainability and feature space analysis techniques to offer an interpretable classification. Our segmentation algorithm achieves an Intersection over Union (IoU) of 0.91, in six databases. Furthermore, the deep-learning classifier achieves an accuracy of 99.9% on testing. The Grad CAM methods and clustering space analysis confirm improved network focus when classifying segmented images compared to non-segmented images. Overall, the proposed visual explainable CAD system has the potential to assist physicians in diagnosing leukemia and improving patient outcomes.

Radiology report generation with a learned knowledge base and multi-modal alignment

In clinics, a radiology report is crucial for guiding a patient's treatment. However, writing radiology reports is a heavy burden for radiologists. To this end, we present an automatic, multi-modal approach for report generation from a chest x-ray. Our approach, motivated by the observation that the descriptions in radiology reports are highly correlated with specific information of the x-ray images, features two distinct modules: (i) Learned knowledge base: To absorb the knowledge embedded in the radiology reports, we build a knowledge base that can automatically distill and restore medical knowledge from textual embedding without manual labor; (ii) Multi-modal alignment: to promote the semantic alignment among reports, disease labels, and images, we explicitly utilize textual embedding to guide the learning of the visual feature space. We evaluate the performance of the proposed model using metrics from both natural language generation and clinic efficacy on the public IU-Xray and MIMIC-CXR datasets. Our ablation study shows that each module contributes to improving the quality of generated reports. Furthermore, the assistance of both modules, our approach outperforms state-of-the-art methods over almost all the metrics. Code is available at https://github.com/LX-doctorAI1/M2KT.

Semantic Embedding Guided Attention with Explicit Visual Feature Fusion for Video Captioning

Video captioning, which bridges vision and language, is a fundamental yet challenging task in computer vision. To generate accurate and comprehensive sentences, both visual and semantic information is quite important. However, most existing methods simply concatenate different types of features and ignore the interactions between them. In addition, there is a large semantic gap between visual feature space and semantic embedding space, making the task very challenging. To address these issues, we propose a framework named semantic embedding guided attention with Explicit visual Feature Fusion for vidEo CapTioning, EFFECT for short, in which we design an explicit visual-feature fusion (EVF) scheme to capture the pairwise interactions between multiple visual modalities and fuse multimodal visual features of videos in an explicit way. Furthermore, we propose a novel attention mechanism called semantic embedding guided attention (SEGA ), which cooperates with the temporal attention to generate a joint attention map. Specifically, in SEGA, the semantic word embedding information is leveraged to guide the model to pay more attention to the most correlated visual features at each decoding stage. In this way, the semantic gap between visual and semantic space is alleviated to some extent. To evaluate the proposed model, we conduct extensive experiments on two widely used datasets, i.e., MSVD and MSR-VTT. The experimental results demonstrate that our approach achieves state-of-the-art results in terms of four evaluation metrics.

LVQ Treatment for Zero-Shot Learning

In image classification, there are no labeled training instances for some classes, which are therefore called unseen classes or test classes. To classify these classes, zero-shot learning (ZSL) was developed, which typically attempts to learn a mapping from the (visual) feature space to the semantic space in which the classes are represented by a list of semantically meaningful attributes. However, the fact that this mapping is learned without using instances of the test classes affects the performance of ZSL, which is known as the domain shift problem. In this study, we propose to apply the learning vector quantization (LVQ) algorithm in the semantic space once the mapping is determined. First and foremost, this allows us to refine the prototypes of the test classes with respect to the learned mapping, which reduces the effects of the domain shift problem. Secondly, the LVQ algorithm increases the margin of the 1-NN classifier used in ZSL, resulting in better classification. Moreover, for this work, we consider a range of LVQ algorithms, from initial to advanced variants, and applied them to a number of state-of-the-art ZSL methods, then obtained their LVQ extensions. The experiments based on five ZSL benchmark datasets showed that the LVQ-empowered extensions of the ZSL methods are superior to their original counterparts in almost all settings.

Interacting-Enhancing Feature Transformer for Cross-Modal Remote-Sensing Image and Text Retrieval

Cross-modal remote sensing image-text retrieval (CMRSITR) is a challenging topic in the remote sensing (RS) community. It has gained growing attention because it can be flexibly used in many practical applications. In the current deep era, with the help of deep convolutional neural networks (DCNNs), many successful CMRSITR methods have been proposed. Most of them first learn valuable features from RS images and texts respectively. Then, the obtained visual and textual features are mapped into a common space for the final retrieval. The above operations are feasible, however, two difficulties are still to be solved. One is that the semantics within the visual and textual features are misaligned due to the independent learning manner. The other one is that the deep links between RS images and texts cannot be fully explored by simple common space mapping. To overcome the above challenges, we propose a new model named interacting-enhancing feature transformer (IEFT) for CMRSITR, which regards the RS images and texts as a whole. First, a simple feature embedding module (FEM) is developed to map images and texts into the visual and textual feature spaces. Second, an information interacting-enhancing module (IIEM) is designed to simultaneously model the inner relationships between RS images and texts and enhance the visual features. IIEM consists of three feature interacting-enhancing (FIE) blocks, each of which contains an inter-modality relationship interacting (IMRI) sub-block and a visual feature enhancing (VFE) sub-block. The duty of IMRI is to exploit the hidden relations between cross-modal data, while the responsibility of VFE is to improve the visual features. By combining them, semantic bias can be mitigated, and the complex contents of RS images can be studied. Finally, the retrieval module (RM) is constructed to generate the matching scores for deciding the search results. Extensive experiments are conducted on four public RS data sets. The positive results demonstrate that our IEFT can achieve superior retrieval performance compared with many existing methods. Our source codes are available at https://github.com/TangXu-Group/Cross-modal-remote-sensing-image-and-text-retrieval-models/tree/main/IEFT.

Application of interactive Genetic Algorithm in landscape planning and design

In order to improve the design effect of garden landscape space environment and optimize the structure of garden landscape space environment, an optimization design method of garden landscape space environment based on interactive genetic algorithm was proposed. Landscape space environment design is built with image visual feature space distributed monitoring model and fuzzy pixel area feature fusion reconstruction model, and the landscape space environment design of the image by multistage decomposition and pixel gray characteristics, established landscape space environment design image visual feature reconstruction model. The method also combines block area template matching method is landscape space environment design of the image features visual reconstruction and visual space distributed detection, information fusion using similarity model reconstructs the landscape space environment design of image visual perception process of information fusion, in order to extract fuzzy characteristic landscape space environment design of the image, Finally, interactive genetic algorithm is used to realize the quality assessment of landscape art information fusion perception and visual reconstruction. The simulation results show that compared with the traditional method, the visual reconstruction quality of landscape spatial environment design image processed by this method is better, the image recognition accuracy is higher, and the output signal-to-noise ratio is improved by 14.6%. The experimental results prove that the introduction of interactive genetic algorithm in landscape planning and design can effectively solve the problems of multi-level feature decomposition and pixel feature separation in the process of landscape design, optimize the landscape spatial environment structure, and achieve good landscape spatial environment design effect.

Feature Detection by Retinal Ganglion Cells.

Retinal circuits transform the pixel representation of photoreceptors into the feature representations of ganglion cells, whose axons transmit these representations to the brain. Functional, morphological, and transcriptomic surveys have identified more than 40 retinal ganglion cell (RGC) types in mice. RGCs extract features of varying complexity; some simply signal local differences in brightness (i.e., luminance contrast), whereas others detect specific motion trajectories. To understand the retina, we need to know how retinal circuits give rise to the diverse RGC feature representations. A catalog of the RGC feature set, in turn, is fundamental to understanding visual processing in the brain. Anterograde tracing indicates that RGCs innervate more than 50 areas in the mouse brain. Current maps connecting RGC types to brain areas are rudimentary, as is our understanding of how retinal signals are transformed downstream to guide behavior. In this article, I review the feature selectivities of mouse RGCs, how they arise, and how they are utilized downstream. Not only is knowledge of the behavioral purpose of RGC signals critical for understanding the retinal contributions to vision; it can also guide us to the most relevant areas of visual feature space.

E2E-V2SResNet: Deep residual convolutional neural networks for end-to-end video driven speech synthesis

Speechreading which infers spoken message from a visually detected articulated facial trend is a challenging task. In this paper, we propose an end-to-end ResNet (E2E-ResNet) model for synthesizing speech signals from the silent video of a speaking individual. The model is the convolutional encoder-decoder framework which captures the frames of video and encodes into a latent space of visual features. The outputs of the decoder are spectrograms which are converted into waveforms corresponding to a speech articulated in the input video. The speech waveforms are then fed to a waveform critic used to decide the real or synthesized speech. The experiments show that the proposed E2E-V2SResNet model is apt to synthesize speech with realism and intelligibility/quality for GRID database. To further demonstrate the potentials of the proposed model, we also conduct experiments on the TCD-TIMIT database. We examine the synthesized speech in unseen speakers using three objective metrics use to measure the intelligibility, quality, and word error rate (WER) of the synthesized speech. We show that E2E-V2SResNet model outscores the competing approaches in most metrics on the GRID and TCD-TIMIT databases. By comparing with the baseline, the proposed model achieved 3.077% improvement in speech quality and 2.593% improvement in speech intelligibility.

Augmented Multimodality Fusion for Generalized Zero-Shot Sketch-Based Visual Retrieval.

Zero-shot sketch-based image retrieval (ZS-SBIR) has attracted great attention recently, due to the potential application of sketch-based retrieval under zero-shot scenarios, where the categories of query sketches and gallery photos are not observed in the training stage. However, it is still under insufficient exploration for the general and practical scenario when the query sketches and gallery photos contain both seen and unseen categories. Such a problem is defined as generalized zero-shot sketch-based image retrieval (GZS-SBIR), which is the focus of this work. To this end, we propose a novel Augmented Multi-modality Fusion (AMF) framework to generalize seen concepts to unobserved ones efficiently. Specifically, a novel knowledge discovery module named cross-domain augmentation is designed in both visual and semantic space to mimic novel knowledge unseen from the training stage, which is the key to handling the GZS-SBIR challenge. Moreover, a triplet domain alignment module is proposed to couple the cross-domain distribution between photo and sketch in visual space. To enhance the robustness of our model, we explore embedding propagation to refine both visual and semantic features by removing undesired noise. Eventually, visual-semantic fusion representations are concatenated for further domain discrimination and task-specific recognition, which tend to trigger the cross-domain alignment in both visual and semantic feature space. Experimental evaluations are conducted on popular ZS-SBIR benchmarks as well as a new evaluation protocol designed for GZS-SBIR from DomainNet dataset with more diverse sub-domains, and the promising results demonstrate the superiority of the proposed solution over other baselines. The source code is available at https://github.com/scottjingtt/AMF_GZS_SBIR.git.

Hierarchical GAN-Tree and Bi-Directional Capsules for multi-label image classification

Compared with the flat multi-label image classification, the hierarchical structure reserves a richer source of structural information to represent complicated relationships between labels in the real world. However, existing multi-label image classification methods focus on the accuracy of label prediction, ignoring the structural information embedded in the hierarchical label space. Furthermore, they hardly form the relevant visual feature space corresponding to the hierarchical label structure. In this paper, we propose a novel hierarchical framework based on the feature and label structural information named Hierarchical GAN-Tree and Bi-Directional Capsules (HGT&BC) to address these problems. We conduct Hierarchical GAN-Tree for feature space representation and Hierarchical Bi-Directional Capsules for label space classification, respectively. Hierarchical GAN-Tree generates hierarchical feature space using the unsupervised divisive clustering pattern according to the hierarchical structure, alleviating the mode-collapse of generators and the overfitting manifestation of conventional GANs. Hierarchical Bi-Directional Capsules utilize the hierarchical label structure in iterations of top-down and bottom-up processes: the top-down process integrates hierarchical relationships into the probability computation to enhance partial hierarchical relationships; the bottom-up process modifies the dynamic routing mechanism between capsules to represent semantic objects for the comprehensive global hierarchical classifiers. Owing to the two components, HGT&BC successfully expresses the hierarchical relationships in both feature and label space and improves the performance of multi-label image classification. Extensive experimental results on four benchmark datasets demonstrate the effectiveness and efficiency of our hierarchical framework in practice.