Auxiliary Classifiers Research Articles

A Novel Active Learning Framework for Cross-Subject Human Activity Recognition from Surface Electromyography.

Wearable sensor-based human activity recognition (HAR) methods hold considerable promise for upper-level control in exoskeleton systems. However, such methods tend to overlook the critical role of data quality and still encounter challenges in cross-subject adaptation. To address this, we propose an active learning framework that integrates the relation network architecture with data sampling techniques. Initially, target data are used to fine tune two auxiliary classifiers of the pre-trained model, thereby establishing subject-specific classification boundaries. Subsequently, we assess the significance of the target data based on classifier discrepancy and partition the data into sample and template sets. Finally, the sampled data and a category clustering algorithm are employed to tune model parameters and optimize template data distribution, respectively. This approach facilitates the adaptation of the model to the target subject, enhancing both accuracy and generalizability. To evaluate the effectiveness of the proposed adaptation framework, we conducted evaluation experiments on a public dataset and a self-constructed electromyography (EMG) dataset. Experimental results demonstrate that our method outperforms the compared methods across all three statistical metrics. Furthermore, ablation experiments highlight the necessity of data screening. Our work underscores the practical feasibility of implementing user-independent HAR methods in exoskeleton control systems.

An extended variational autoencoder for cross-subject electromyograph gesture recognition

Surface electromyographic hand gesture recognition has gained significant attention in recent years, especially within the field of human–computer interfaces. However, cross-subject tasks remain challenging due to inherent individual differences. To address this, a novel approach for hand gesture recognition is proposed that leverages a subject-generalized variational autoencoder. This approach involves an extended variational autoencoder designed to disentangle input data into three distinct feature-specific representations. The primary classifier within the variational autoencoder focuses on gesture recognition, while two auxiliary classifiers work together to extract subject-specific and gesture-specific features. The gesture-specific features capture generalized characteristics applicable across all subjects, enabling direct application to new subjects. To enhance accuracy and stability, a competitive voting strategy is implemented. The effectiveness of the proposed method was evaluated using a dataset comprising six representative gestures performed by eight subjects. Comparative analysis with baseline models shows that our approach outperforms others, demonstrating superior generalization with an average accuracy of 90.52% in cross-subject validation.

A Novel Multiobjective Genetic Programming Approach to High-Dimensional Data Classification.

The development of data sensing technology has generated a vast amount of high-dimensional data, posing great challenges for machine learning models. Over the past decades, despite demonstrating its effectiveness in data classification, genetic programming (GP) has still encountered three major challenges when dealing with high-dimensional data: 1) solution diversity; 2) multiclass imbalance; and 3) large feature space. In this article, we have developed a problem-specific multiobjective GP framework (PS-MOGP) for handling classification tasks with high-dimensional data. To reduce the large solution space caused by high dimensionality, we incorporate the recursive feature elimination strategy based on mining the archive of evolved GP solutions. A progressive domination Pareto archive evolution strategy (PD-PAES), which optimizes the objectives in a specific order according to their objectives, is proposed to evaluate the GP individuals and maintain a better diversity of solutions. Besides, to address the seriously imbalanced class issue caused by traditional binary decomposition (BD) one versus rest (OVR) for multiclass classification problems, we design a method named BD with a similar positive and negative class size (BD-SPNCS) to generate a set of auxiliary classifiers. Experimental results on benchmark and real-world datasets demonstrate that our proposed PS-MOGP outperforms state-of-the-art traditional and evolutionary classification methods in the context of high-dimensional data classification.

A dual-path model merging CNN and RNN with attention mechanism for crop classification

Rapid and accurate crop classification is essential for estimating crop information and improving cropland management. The application of deep learning models for crop classification using time-series data has become the most promising method. However, most approaches rely on single models for data processing result in lower classification accuracy and poor stability. Therefore, this study proposes a dual-path approach with attention mechanisms (DPACR) to promote the performance of this model architecture in crop classification using time series data. Specifically, the model comprises two branches, the Recurrent neural network (RNN) branch with bidirectional gated recurrent units (GRU) with a self-attention mechanism, and the convolutional neural network (CNN) branch based on SE-ResNet. Crop classification is accomplished by a main classifier, supported by auxiliary classifiers from the two branches. Using the Google Earth Engine and the Sentinel-2 satellite data, DPACR was tested in the Hetao irrigation district in Inner Mongolia, China. The comparison experiment demonstrated that the DPACR achieved the highest overall accuracy (OA = 0.959) and Kappa coefficient (Kappa = 0.941) compared to other five models (MLP, SE-ResNet, Bi-At-GRU, SVM, and RF). DPACR excelled in classifying six crops, maintaining high accuracy across multiple classes. Compared to attention mechanisms, auxiliary classifiers can significantly improve classification performance. This study highlights the effective combination of cloud computing and deep learning for large-scale crop classification, providing a practical method for agricultural monitoring and management.

MOCAT: multi-omics integration with auxiliary classifiers enhanced autoencoder

BackgroundIntegrating multi-omics data is emerging as a critical approach in enhancing our understanding of complex diseases. Innovative computational methods capable of managing high-dimensional and heterogeneous datasets are required to unlock the full potential of such rich and diverse data.MethodsWe propose a Multi-Omics integration framework with auxiliary Classifiers-enhanced AuToencoders (MOCAT) to utilize intra- and inter-omics information comprehensively. Additionally, attention mechanisms with confidence learning are incorporated for enhanced feature representation and trustworthy prediction.ResultsExtensive experiments were conducted on four benchmark datasets to evaluate the effectiveness of our proposed model, including BRCA, ROSMAP, LGG, and KIPAN. Our model significantly improved most evaluation measurements and consistently surpassed the state-of-the-art methods. Ablation studies showed that the auxiliary classifiers significantly boosted classification accuracy in the ROSMAP and LGG datasets. Moreover, the attention mechanisms and confidence evaluation block contributed to improvements in the predictive accuracy and generalizability of our model.ConclusionsThe proposed framework exhibits superior performance in disease classification and biomarker discovery, establishing itself as a robust and versatile tool for analyzing multi-layer biological data. This study highlights the significance of elaborated designed deep learning methodologies in dissecting complex disease phenotypes and improving the accuracy of disease predictions.

Adversarial Domain Adaptation with Dual Auxiliary Classifiers for Cross-Domain Open Set Intelligent Fault Diagnosis

Adversarial Domain Adaptation with Dual Auxiliary Classifiers for Cross-Domain Open Set Intelligent Fault Diagnosis

Facial Emotion Recognition Combining Auxiliary Classifiers and Multiscale CBAM Attention Mechanisms

Facial Emotion Recognition Combining Auxiliary Classifiers and Multiscale CBAM Attention Mechanisms

LoCoExNet: Low-Cost Early Exit Network for Energy Efficient CNN Accelerator Design

Early exit techniques, where the inference process of convolutional neural networks (CNNs) is early terminated by using auxiliary classifiers (called branches) to reduce data processing energy for easy inputs, have been actively researched. However, the conventional early exit works have suffered from the large size of branches, whose memory access energy is significantly large compared to that of the main network. In this paper, we propose a low-cost early exit network (LoCoExNet), which significantly improves energy efficiencies by reducing the parameters used in inference with efficient branch structures. To further reduce the energy consumption of branches, based on the observation that the classification difficulties of the images can be predicted using the magnitudes of input activations, we also propose hardware-friendly dynamic branch pruning (DBP). Given the network and target dataset, we can construct an energy-efficient early exit network through the branch structure determination algorithm and DBP algorithm. Finally, we develop several architectural supporting modules to improve the energy efficiency of the proposed LoCoExNet with DBP. The experimental results show that the LoCoExNet uses 28.7% of the total network parameters on average for Tiny-ImageNet dataset using VGG-16 without accuracy loss. The CNN accelerator that implements LoCoExNet with DBP has been implemented using the 65nm CMOS process. The implementation results show that the LoCoExNet accelerator achieves up to 91% of energy savings and up to 4.46× of speedups without accuracy loss for CIFAR-10 dataset using VGG-16 compared to the state-of-the-art CNN accelerators.

Group-Fusion One-Dimensional Convolutional Neural Network for Ballistic Target High-Resolution Range Profile Recognition with Layer-Wise Auxiliary Classifiers

Ballistic missile defense systems require accurate target recognition technology. Effective feature extraction is crucial for this purpose. The deep convolutional neural network (CNN) has proven to be an effective method for recognizing high-resolution range profiles (HRRPs) of ballistic targets. It excels in perceiving local features and extracting robust features. However, the standard CNN's fully connected manner results in high computational complexity, which is unsuitable for deployment in real-time missile defense systems with stringent performance requirements. To address the issue of computational complexity in HRRP recognition based on the standard one-dimensional CNN (1DCNN), we propose a lightweight network called group-fusion 1DCNN with layer-wise auxiliary classifiers (GFAC-1DCNN). GFAC-1DCNN employs group convolution (G-Conv) instead of standard convolution to effectively reduce model complexity. Simply using G-Conv, however, may decrease model recognition accuracy due to the lack of information flow between feature maps generated by each G-Conv. To overcome this limitation, we introduce a linear fusion layer to combine the output features of G-Convs, thereby improving recognition accuracy. Additionally, besides the main classifier at the deepest layer, we construct layer-wise auxiliary classifiers for different hierarchical features. The results from all classifiers are then fused for comprehensive target recognition. Extensive experiments demonstrate that GFAC-1DCNN with such simple and effective techniques achieves higher overall testing accuracy than state-of-the-art ballistic target HRRP recognition models, while significantly reducing model complexity. It also exhibits a higher recall rate for warhead recognition compared to other methods. Based on these compelling results, we believe this work is valuable in reducing workload and enhancing missile interception rates in missile defense systems.

Neighbor self-knowledge distillation

Self-Knowledge Distillation (Self-KD), a technique that enables neural networks to learn from themselves, often relies on auxiliary modules or networks to generate supervisory signals for training. However, this approach incurs significant additional resource costs. Moreover, incorporating auxiliary classifiers within the network architecture creates a capacity mismatch when distilling knowledge from deep to shallow classifiers. This paper proposes a concise and efficient Self-KD method called Neighbor Self-Knowledge Distillation (NSKD), which introduces teacher assistants into the Self-KD by adding auxiliary classifiers to the shallow part of the network to construct distillations of multiple neighboring student-teacher assistant combinations to reduce the mismatch between the students' and teachers' abilities. During distillation, NSKD utilizes only the soft labels generated by each classifier and corresponding ground truth labels as supervisory signals, minimizing resource consumption. NSKD enables neighboring modules to learn from each other through neighboring distillation, enhancing overall network performance. Experimental results on five network models and seven popular datasets demonstrate the superiority of NSKD over other state-of-the-art Self-KD methods. Notably, NSKD achieves average accuracy improvements of 2.26%, 2.32%, and 2.4% on the CIFAR100, TinyImageNet, and fine-grained visual classification datasets.

Semantic alignment with self-supervision for class incremental learning

Existing class incremental learning methods typically employ knowledge distillation to minimize discrepancies in model outputs. However, these methods are restricted by the mismatch between quondam knowledge and new data. To alleviate these issues, we introduce semantic alignment decouples the classification and distillation in different semantic spaces. The unmatched new data is regarded as out-of-distribution data on the old class distribution, and the corresponding pseudo-labels are attached to the new data using the original network. Intuitively, the pseudo-labels could be consistently preserved in the old semantic space. Moreover, we develop auxiliary self-supervised classifiers to learn more generalized representation, enabling a better stability-plastic trade-off. Furthermore, self-distillation is employed to refine self-supervised knowledge from auxiliary classifiers. Extensive experiments demonstrate that our method achieves the best performance on CIFAR100, ImageNet100, ImageNet, CUB200, and Stanford-Dogs120 datasets. Notably, our method outperforms existing methods by a substantial margin when only one old exemplar is stored per class, i.e., 11.34% and 21.46% improvement on CIFAR100 of 5 phases and 10 phases, respectively.

Deep learning model for distinguishing Mayo endoscopic subscore 0 and 1 in patients with ulcerative colitis

The aim of this study was to address the issue of differentiating between Mayo endoscopic subscore (MES) 0 and MES 1 using a deep learning model. A dataset of 492 ulcerative colitis (UC) patients who demonstrated MES improvement between January 2018 and December 2019 at Samsung Medical Center was utilized. Specifically, two representative images of the colon and rectum were selected from each patient, resulting in a total of 984 images for analysis. The deep learning model utilized in this study consisted of a convolutional neural network (CNN)-based encoder, with two auxiliary classifiers for the colon and rectum, as well as a final MES classifier that combined image features from both inputs. In the internal test, the model achieved an F1-score of 0.92, surpassing the performance of seven novice classifiers by an average margin of 0.11, and outperforming their consensus by 0.02. The area under the receiver operating characteristic curve (AUROC) was calculated to be 0.97 when considering MES 1 as positive, with an area under the precision-recall curve (AUPRC) of 0.98. In the external test using the Hyperkvasir dataset, the model achieved an F1-score of 0.89, AUROC of 0.86, and AUPRC of 0.97. The results demonstrate that the proposed CNN-based model, which integrates image features from both the colon and rectum, exhibits superior performance in accurately discriminating between MES 0 and MES 1 in patients with UC.

A novel domain generalization network with multidomain specific auxiliary classifiers for machinery fault diagnosis under unseen working conditions

The domain adaptation-based intelligent diagnosis approaches have achieved promising performance on diagnosis tasks under different working conditions. However, these methods rely on a premise that the target data are available in the model training phase. In real industries, collecting interest data from target machines in advance may be infeasible, which greatly restricts the practicality of intelligent diagnosis approaches in reality. To solve this issue, this study proposes a novel domain generalization network for machinery fault diagnosis where interest data are completely unavailable during model training. In the proposed network, multiple domain-specific auxiliary classifiers are firstly designed to effectively learn domain-specific features from each source domain, and then, a convolutional auto-encoder module is further constructed to map raw signals into a new feature space where the learned domain-specific features are removed. Meanwhile, with the features outputted by the convolutional auto-encoder, a domain-invariant classifier with inter-domain alignment strategy is designed to learn generalization diagnostic knowledge among different source domains, thereby performing diagnosis tasks under unseen conditions. Experiments on three practical rotary machinery datasets validate the effectiveness of the proposed network, showing that the proposed network is promising for fault diagnosis tasks in practical scenarios.

A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise

As deep neural networks can easily overfit noisy labels, robust training in the presence of noisy labels is becoming an important challenge in modern deep learning. While existing methods address this problem in various directions, they still produce unpredictable sub-optimal results since they rely on the posterior information estimated by the feature extractor corrupted by noisy labels. Lipschitz regularization successfully alleviates this problem by training a robust feature extractor, but it requires longer training time and expensive computations. Motivated by this, we propose a simple yet effective method, called ALASCA, which efficiently provides a robust feature extractor under label noise. ALASCA integrates two key ingredients: (1) adaptive label smoothing based on our theoretical analysis that label smoothing implicitly induces Lipschitz regularization, and (2) auxiliary classifiers that enable practical application of intermediate Lipschitz regularization with negligible computations. We conduct wide-ranging experiments for ALASCA and combine our proposed method with previous noise-robust methods on several synthetic and real-world datasets. Experimental results show that our framework consistently improves the robustness of feature extractors and the performance of existing baselines with efficiency.

Multi-Classifier Adversarial Optimization for Active Learning

Active learning (AL) aims to find a better trade-off between labeling costs and model performance by consciously selecting more informative samples to label. Recently, adversarial approaches have emerged as effective solutions. Most of them leverage generative adversarial networks to align feature distributions of labeled and unlabeled data, upon which discriminators are trained to better distinguish between them. However, these methods fail to consider the relationship between unlabeled samples and decision boundaries, and their training processes are often complex and unstable. To this end, this paper proposes a novel adversarial AL method, namely multi-classifier adversarial optimization for active learning (MAOAL). MAOAL employs task-specific decision boundaries for data alignment while selecting the most informative samples to label. To fulfill this, we introduce a novel classifier class confusion (C3) metric, which represents the classifier discrepancy as the inter-class correlation of classifier outputs. Without any additional hyper-parameters, the C3 metric further reduces the negative impacts of ambiguous samples in the process of distribution alignment and sample selection. More concretely, the network is trained adversarially by adding two auxiliary classifiers, reducing the distribution bias of labeled and unlabeled samples by minimizing the C3 loss between classifiers, while learning tighter decision boundaries and highlighting hard samples by maximizing the C3 loss. Finally, the unlabeled samples with the highest C3 loss are selected to label. Extensive experiments demonstrate the superiority of our approach over state-of-the-art AL methods in terms of image classification and object detection.

Combining historical aerial photography with machine learning to map landscape change impacts on dry grasslands in the Central Alps

ContextStriking land-use changes after WW II characterize the past century in the European Alps with impact on ecosystems and biodiversity. Documenting land-use changes is often difficult due to limited information from the past. Mapping landscape history with aerial photography can foster the understanding of human-induced changes in vulnerable ecosystems, such as the remnants of dry grasslands in the Central Alps.ObjectivesWe aimed to assess changes in grassland vegetation and their current extent in Val Venosta (European Alps, Italy) in relation to overall landscape settings, anthropogenic drivers of change and the effectiveness of the protected areas.MethodsWe performed a land-cover classification based on a mixed machine learning approach including several auxiliary classifiers in a random forest model to characterise the extent and state of (dry) grasslands. We calculated landscape metrics between 1945 and 2015 to assess shape-related changes, especially regarding their landscape embedding and the protection status of sites.ResultsThree main processes related to a changing extent in grassland habitat prevail: (i) agricultural intensification, (ii) settlement expansion at the valley bottom and (iii) forest expansion (afforestation and encroachment due to decreasing pasture activities) on the valley slopes. The remaining grassland habitat is increasingly isolated and fragmented, leaving only few core areas of dry grassland, which tended to be better conserved within protected areas.ConclusionThe changes in extent of dry grasslands revealed marked changes. Transformations are assumed to be predominantly caused by human impact and successional changes. Our results confirm the importance of protected area networks. The pronounced landscape changes underline the urgent need for future research with explicit focus on the changes at community level and the underlying causes. Identifying all relevant drivers of change should be a key element in targeted conservation efforts.

Dual generative adversarial networks combining conditional assistance and feature enhancement for imbalanced fault diagnosis

The dataset in the application scenario of existing fault diagnosis methods is often balanced, while the data collected under actual working conditions are often imbalanced. Directly applying existing fault diagnosis methods to this scenario will lead to poor diagnosis effect. In view of the above problems, we proposed a method called dual generative adversarial networks (DGANs) combining conditional assistance and feature enhancement. The method uses data augmentation as a basic strategy to supplement imbalanced datasets by generating high-quality data. Firstly, a new generator is designed to build the basic framework by sharing the dual-branch deconvolutional neural networks, and combining the label auxiliary information and the coral distance loss function to ensure the diversity of generated samples. Secondly, a new discriminator was designed, which is based on deep convolutional neural networks and embedded with auxiliary classifiers, further expanding the function of the discriminator. Thirdly, the self-attention module is introduced into both the generator and the discriminator to enhance deep feature learning and improve the quality of generated samples; finally, the proposed method is experimentally validated on datasets of two different testbeds. The experimental results show that the proposed method can generate fake samples with rich diversity and high quality, using these samples to supplement the imbalanced dataset, the effect of imbalanced fault diagnosis has been substantially improved. This method can be used to solve the problem of fault diagnosis in the case of sample imbalance, which often exists in actual working conditions.

SCL-Net: Structured Collaborative Learning for PET/CT Based Tumor Segmentation.

Collaborative learning methods for medical image segmentation are often variants of UNet, where the constructions of classifiers depend on each other and their outputs are supervised independently. However, they cannot explicitly ensure that optimizing auxiliary classifier heads leads to improved segmentation of target classifier. To resolve this problem, we propose a structured collaborative learning (SCL) method, which consists of a context-aware structured classifier population generation (CA-SCPG) module, where the feature propagation of the target classifier path is directly enhanced by the outputs of auxiliary classifiers via a light-weighted high-level context-aware dense connection (HLCA-DC) mechanism, and a knowledge-aware structured classifier population supervision (KA-SCPS) module, where the auxiliary classifiers are properly supervised under the guidance of target classifier's segmentations. Specifically, SCL is proposed based on a recurrent-dense-siamese decoder (RDS-Decoder), which consists of multiple siamese-decoder paths. CA-SCPG enhances the feature propagation of the decoder paths by HLCA-DC, which densely reuses previous decoder paths' output prediction maps to belong to the target classes as inputs to the layers of latter decoder paths. KA-SCPS supervises the classifier heads simultaneously with KA-SCPS loss, which consists of a generalized weighted cross-entropy loss for deep class-imbalanced learning and a novel knowledge-aware Dice loss (KA-DL). KA-DL is a weighted Dice loss broadcasting knowledges learnt by the target classifier to other classifier heads, harmonizing the learning process of the classifier population. Experiments are performed based on PET/CT volumes with malignant melanoma, lymphoma, or lung cancer. Experimental results demonstrate the superiority of our SCL, when compared to the state-of-the-art methods and baselines.

P254 Deep Learning Model for Distinguishing MES 0 and MES 1 in Patients with Ulcerative Colitis

Abstract Background Endoscopic remission has recently been defined as a Mayo endoscopic sub-score (MES) of 0. Therefore, patients with MES 1 need to step up to achieve an MES of 0 on the endoscopic score. In discriminating between MES 0 and 1, the inter-observer variation was very severe among the endoscopists. This study aimed to narrow the gap in distinguishing between MES 0 and MES1 using a deep learning model. Methods From the endoscopic images of 492 ulcerative colitis (UC) patients with MES improvement (MES 0 or MES 1) from January 2018 to December 2019 at this center, two representative images of the colon and rectum were selected, and a total of 984 images were analyzed. Our model was composed of a convolutional neural network (CNN)-based encoder, two auxiliary classifiers for the colon and rectum, and a final MES classifier for the combined image features of the two inputs. The following three experiments were conducted to validate and test the proposed model: 12-fold cross-validation for representative model selection, performance comparison with a novice group through an internal test dataset, and an external test with Hyperkvasir, a public gastrointestinal endoscopic image dataset. Results In the internal test, our model showed an F1-score of 0.92. This was, on average, 0.11 higher than each of the seven novices and 0.02 higher than their consensus. Considering MES 1 as positive, the area under the receiver operating characteristic curve (AUROC) was 0.97, and the area under the precision-recall curve (AUPRC) was 0.98. In the external test with Hyperkvasir, our model showed an F1-score of 0.89, AUROC of 0.86, and AUPRC of 0.97. Conclusion We found that the proposed CNN-based model that integrates the image features of the colon and rectum has superior performance in discriminating between MES 0 and MES 1 in patients with UC. Further prospective studies are required to prove the clinical utility of our model in clinical practice.

Prototype-Guided Multitask Adversarial Network for Cross-Domain LiDAR Point Clouds Semantic Segmentation

Unsupervised domain adaptation (UDA) segmentation aims to leverage labeled source data to make accurate predictions on unlabeled target data. The key is to make the segmentation network learn domain-invariant representations. In this work, we propose a prototype-guided multitask adversarial network (PMAN) to achieve this. First, we propose an intensity-aware segmentation network (IAS-Net) that leverages the private intensity information of target data to substantially facilitate feature learning of the target domain. Second, the category-level cross-domain feature alignment strategy is introduced to flee the side effects of global feature alignment. It employs the prototype (class centroid) and includes two essential operations: 1) build an auxiliary nonparametric classifier to evaluate the semantic alignment degree of each point based on the prediction consistency between the main and auxiliary classifiers and 2) introduce two class-conditional point-to-prototype learning objectives for better alignment. One is to explicitly perform category-level feature alignment in a progressive manner, and the other aims to shape the source feature representation to be discriminative. Extensive experiments reveal that our PMAN outperforms state-of-the-art results on two benchmark datasets.