Zhihai He

Yushun Tang, Ce Zhang, Heng Xu et al. · cmu

Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. We take inspiration from the biological plausibility learning where the neuron responses are tuned based on a local synapse-change procedure and activated by competitive lateral inhibition rules. Based on these feed-forward learning rules, we design a soft Hebbian learning process which provides an unsupervised and effective mechanism for online adaptation. We observe that the performance of this feed-forward Hebbian learning for fully test-time adaptation can be significantly improved by incorporating a feedback neuro-modulation layer. It is able to fine-tune the neuron responses based on the external feedback generated by the error back-propagation from the top inference layers. This leads to our proposed neuro-modulated Hebbian learning (NHL) method for fully test-time adaptation. With the unsupervised feed-forward soft Hebbian learning being combined with a learned neuro-modulator to capture feedback from external responses, the source model can be effectively adapted during the testing process. Experimental results on benchmark datasets demonstrate that our proposed method can significantly improve the adaptation performance of network models and outperforms existing state-of-the-art methods.

Yushun Tang, Shuoshuo Chen, Zhihe Lu et al.

Transformer-based methods have achieved remarkable success in various machine learning tasks. How to design efficient test-time adaptation methods for transformer models becomes an important research task. In this work, motivated by the dual-subband wavelet lifting scheme developed in multi-scale signal processing which is able to efficiently separate the input signals into principal components and noise components, we introduce a dual-path token lifting for domain shift correction in test time adaptation. Specifically, we introduce an extra token, referred to as \textit{domain shift token}, at each layer of the transformer network. We then perform dual-path lifting with interleaved token prediction and update between the path of domain shift tokens and the path of class tokens at all network layers. The prediction and update networks are learned in an adversarial manner. Specifically, the task of the prediction network is to learn the residual noise of domain shift which should be largely invariant across all classes and all samples in the target domain. In other words, the predicted domain shift noise should be indistinguishable between all sample classes. On the other hand, the task of the update network is to update the class tokens by removing the domain shift from the input image samples so that input samples become more discriminative between different classes in the feature space. To effectively learn the prediction and update networks with two adversarial tasks, both theoretically and practically, we demonstrate that it is necessary to use smooth optimization for the update network but non-smooth optimization for the prediction network. Experimental results on the benchmark datasets demonstrate that our proposed method significantly improves the online fully test-time domain adaptation performance. Code is available at \url{https://github.com/yushuntang/DPAL}.

Shichao Kan, Yixiong Liang, Min Li et al.

A fundamental challenge in deep metric learning is the generalization capability of the feature embedding network model since the embedding network learned on training classes need to be evaluated on new test classes. To address this challenge, in this paper, we introduce a new method called coded residual transform (CRT) for deep metric learning to significantly improve its generalization capability. Specifically, we learn a set of diversified prototype features, project the feature map onto each prototype, and then encode its features using their projection residuals weighted by their correlation coefficients with each prototype. The proposed CRT method has the following two unique characteristics. First, it represents and encodes the feature map from a set of complimentary perspectives based on projections onto diversified prototypes. Second, unlike existing transformer-based feature representation approaches which encode the original values of features based on global correlation analysis, the proposed coded residual transform encodes the relative differences between the original features and their projected prototypes. Embedding space density and spectral decay analysis show that this multi-perspective projection onto diversified prototypes and coded residual representation are able to achieve significantly improved generalization capability in metric learning. Finally, to further enhance the generalization performance, we propose to enforce the consistency on their feature similarity matrices between coded residual transforms with different sizes of projection prototypes and embedding dimensions. Our extensive experimental results and ablation studies demonstrate that the proposed CRT method outperform the state-of-the-art deep metric learning methods by large margins and improving upon the current best method by up to 4.28% on the CUB dataset.

Yushun Tang, Qinghai Guo, Zhihai He

One central challenge in source-free unsupervised domain adaptation (UDA) is the lack of an effective approach to evaluate the prediction results of the adapted network model in the target domain. To address this challenge, we propose to explore a new method called cross-inferential networks (CIN). Our main idea is that, when we adapt the network model to predict the sample labels from encoded features, we use these prediction results to construct new training samples with derived labels to learn a new examiner network that performs a different but compatible task in the target domain. Specifically, in this work, the base network model is performing image classification while the examiner network is tasked to perform relative ordering of triplets of samples whose training labels are carefully constructed from the prediction results of the base network model. Two similarity measures, cross-network correlation matrix similarity and attention consistency, are then developed to provide important guidance for the UDA process. Our experimental results on benchmark datasets demonstrate that our proposed CIN approach can significantly improve the performance of source-free UDA.

Zhehan Kan, Shuoshuo Chen, Zeng Li et al.

We observe that human poses exhibit strong group-wise structural correlation and spatial coupling between keypoints due to the biological constraints of different body parts. This group-wise structural correlation can be explored to improve the accuracy and robustness of human pose estimation. In this work, we develop a self-constrained prediction-verification network to characterize and learn the structural correlation between keypoints during training. During the inference stage, the feedback information from the verification network allows us to perform further optimization of pose prediction, which significantly improves the performance of human pose estimation. Specifically, we partition the keypoints into groups according to the biological structure of human body. Within each group, the keypoints are further partitioned into two subsets, high-confidence base keypoints and low-confidence terminal keypoints. We develop a self-constrained prediction-verification network to perform forward and backward predictions between these keypoint subsets. One fundamental challenge in pose estimation, as well as in generic prediction tasks, is that there is no mechanism for us to verify if the obtained pose estimation or prediction results are accurate or not, since the ground truth is not available. Once successfully learned, the verification network serves as an accuracy verification module for the forward pose prediction. During the inference stage, it can be used to guide the local optimization of the pose estimation results of low-confidence keypoints with the self-constrained loss on high-confidence keypoints as the objective function. Our extensive experimental results on benchmark MS COCO and CrowdPose datasets demonstrate that the proposed method can significantly improve the pose estimation results.

Heng Xu, Bowen Hai, Yushun Tang et al.

Learned Image Compression (LIC) models have achieved superior rate-distortion performance than traditional codecs. Existing LIC models use CNN, Transformer, or Mixed CNN-Transformer as basic blocks. However, limited by the shifted window attention, Swin-Transformer-based LIC exhibits a restricted growth of receptive fields, affecting the ability to model large objects for image compression. To address this issue and improve the performance, we incorporate window partition into channel attention for the first time to obtain large receptive fields and capture more global information. Since channel attention hinders local information learning, it is important to extend existing attention mechanisms in Transformer codecs to the space-channel attention to establish multiple receptive fields, being able to capture global correlations with large receptive fields while maintaining detailed characterization of local correlations with small receptive fields. We also incorporate the discrete wavelet transform into our Spatial-Channel Hybrid (SCH) framework for efficient frequency-dependent down-sampling and further enlarging receptive fields. Experiment results demonstrate that our method achieves state-of-the-art performances, reducing BD-rate by 18.54%, 23.98%, 22.33%, and 24.71% on four standard datasets compared to VTM-23.1.

Siqi Wu, Yinda Chen, Dong Liu et al.

In this paper, we study how to synthesize a dynamic reference from an external dictionary to perform conditional coding of the input image in the latent domain and how to learn the conditional latent synthesis and coding modules in an end-to-end manner. Our approach begins by constructing a universal image feature dictionary using a multi-stage approach involving modified spatial pyramid pooling, dimension reduction, and multi-scale feature clustering. For each input image, we learn to synthesize a conditioning latent by selecting and synthesizing relevant features from the dictionary, which significantly enhances the model's capability in capturing and exploring image source correlation. This conditional latent synthesis involves a correlation-based feature matching and alignment strategy, comprising a Conditional Latent Matching (CLM) module and a Conditional Latent Synthesis (CLS) module. The synthesized latent is then used to guide the encoding process, allowing for more efficient compression by exploiting the correlation between the input image and the reference dictionary. According to our theoretical analysis, the proposed conditional latent coding (CLC) method is robust to perturbations in the external dictionary samples and the selected conditioning latent, with an error bound that scales logarithmically with the dictionary size, ensuring stability even with large and diverse dictionaries. Experimental results on benchmark datasets show that our new method improves the coding performance by a large margin (up to 1.2 dB) with a very small overhead of approximately 0.5\% bits per pixel. Our code is publicly available at https://github.com/ydchen0806/CLC.

Weiming Chen, Yijia Wang, Zhihan Zhu et al.

We consider the problem of ultra-low bit rate visual communication for remote vision analysis, human interactions and control in challenging scenarios with very low communication bandwidth, such as deep space exploration, battlefield intelligence, and robot navigation in complex environments. In this paper, we ask the following important question: can we accurately reconstruct the visual scene using only a very small portion of the bit rate in existing coding methods while not sacrificing the accuracy of vision analysis and performance of human interactions? Existing text-to-image generation models offer a new approach for ultra-low bitrate image description. However, they can only achieve a semantic-level approximation of the visual scene, which is far insufficient for the purpose of visual communication and remote vision analysis and human interactions. To address this important issue, we propose to seamlessly integrate image generation with deep image compression, using joint text and coding latent to guide the rectified flow models for precise generation of the visual scene. The semantic text description and coding latent are both encoded and transmitted to the decoder at a very small bit rate. Experimental results demonstrate that our method can achieve the same image reconstruction quality and vision analysis accuracy as existing methods while using much less bandwidth. The code will be released upon paper acceptance.

Siyi Liu, Weiming Chen, Yushun Tang et al.

Diffusion-based Image Editing has achieved significant success in recent years. However, it remains challenging to achieve high-quality image editing while maintaining the background similarity without sacrificing speed or memory efficiency. In this work, we introduce LatentEdit, an adaptive latent fusion framework that dynamically combines the current latent code with a reference latent code inverted from the source image. By selectively preserving source features in high-similarity, semantically important regions while generating target content in other regions guided by the target prompt, LatentEdit enables fine-grained, controllable editing. Critically, the method requires no internal model modifications or complex attention mechanisms, offering a lightweight, plug-and-play solution compatible with both UNet-based and DiT-based architectures. Extensive experiments on the PIE-Bench dataset demonstrate that our proposed LatentEdit achieves an optimal balance between fidelity and editability, outperforming the state-of-the-art method even in 8-15 steps. Additionally, its inversion-free variant further halves the number of neural function evaluations and eliminates the need for storing any intermediate variables, substantially enhancing real-time deployment efficiency.

Zhiqun Zhao, Hengyou Wang, Hao Sun et al.

Deep neural networks recognize objects by analyzing local image details and summarizing their information along the inference layers to derive the final decision. Because of this, they are prone to adversarial attacks. Small sophisticated noise in the input images can accumulate along the network inference path and produce wrong decisions at the network output. On the other hand, human eyes recognize objects based on their global structure and semantic cues, instead of local image textures. Because of this, human eyes can still clearly recognize objects from images which have been heavily damaged by adversarial attacks. This leads to a very interesting approach for defending deep neural networks against adversarial attacks. In this work, we propose to develop a structure-preserving progressive low-rank image completion (SPLIC) method to remove unneeded texture details from the input images and shift the bias of deep neural networks towards global object structures and semantic cues. We formulate the problem into a low-rank matrix completion problem with progressively smoothed rank functions to avoid local minimums during the optimization process. Our experimental results demonstrate that the proposed method is able to successfully remove the insignificant local image details while preserving important global object structures. On black-box, gray-box, and white-box attacks, our method outperforms existing defense methods (by up to 12.6%) and significantly improves the adversarial robustness of the network.

Hao Sun, Zhiqun Zhao, Zhihai He

We observe that the human trajectory is not only forward predictable, but also backward predictable. Both forward and backward trajectories follow the same social norms and obey the same physical constraints with the only difference in their time directions. Based on this unique property, we develop a new approach, called reciprocal learning, for human trajectory prediction. Two networks, forward and backward prediction networks, are tightly coupled, satisfying the reciprocal constraint, which allows them to be jointly learned. Based on this constraint, we borrow the concept of adversarial attacks of deep neural networks, which iteratively modifies the input of the network to match the given or forced network output, and develop a new method for network prediction, called reciprocal attack for matched prediction. It further improves the prediction accuracy. Our experimental results on benchmark datasets demonstrate that our new method outperforms the state-of-the-art methods for human trajectory prediction.

Yang Li, Jianhe Yuan, Zhiqun Zhao et al.

In this work, we develop a joint sample discovery and iterative model evolution method for semi-supervised learning on very small labeled training sets. We propose a master-teacher-student model framework to provide multi-layer guidance during the model evolution process with multiple iterations and generations. The teacher model is constructed by performing an exponential moving average of the student models obtained from past training steps. The master network combines the knowledge of the student and teacher models with additional access to newly discovered samples. The master and teacher models are then used to guide the training of the student network by enforcing the consistence between their predictions of unlabeled samples and evolve all models when more and more samples are discovered. Our extensive experiments demonstrate that the discovering confident samples from the unlabeled dataset, once coupled with the above master-teacher-student network evolution, can significantly improve the overall semi-supervised learning performance. For example, on the CIFAR-10 dataset, with a very small set of 250 labeled samples, our method achieves an error rate of 11.81 %, more than 38 % lower than the state-of-the-art method Mean-Teacher (49.91 %).

Zhi Zhang, Guanghan Ning, Yigang Cen et al.

The inference structures and computational complexity of existing deep neural networks, once trained, are fixed and remain the same for all test images. However, in practice, it is highly desirable to establish a progressive structure for deep neural networks which is able to adapt its inference process and complexity for images with different visual recognition complexity. In this work, we develop a multi-stage progressive structure with integrated confidence analysis and decision policy learning for deep neural networks. This new framework consists of a set of network units to be activated in a sequential manner with progressively increased complexity and visual recognition power. Our extensive experimental results on the CIFAR-10 and ImageNet datasets demonstrate that the proposed progressive deep neural network is able to obtain more than 10 fold complexity scalability while achieving the state-of-the-art performance using a single network model satisfying different complexity-accuracy requirements.

Guanghan Ning, Zhihai He

The task of multi-person human pose estimation in natural scenes is quite challenging. Existing methods include both top-down and bottom-up approaches. The main advantage of bottom-up methods is its excellent tradeoff between estimation accuracy and computational cost. We follow this path and aim to design smaller, faster, and more accurate neural networks for the regression of keypoints and limb association vectors. These two regression tasks are naturally dependent on each other. In this work, we propose a dual-path network specially designed for multi-person human pose estimation, and compare our performance with the openpose network in aspects of model size, forward speed, and estimation accuracy.

Zhi Zhang, Guanghan Ning, Zhihai He

While deeper and wider neural networks are actively pushing the performance limits of various computer vision and machine learning tasks, they often require large sets of labeled data for effective training and suffer from extremely high computational complexity. In this paper, we will develop a new framework for training deep neural networks on datasets with limited labeled samples using cross-network knowledge projection which is able to improve the network performance while reducing the overall computational complexity significantly. Specifically, a large pre-trained teacher network is used to observe samples from the training data. A projection matrix is learned to project this teacher-level knowledge and its visual representations from an intermediate layer of the teacher network to an intermediate layer of a thinner and faster student network to guide and regulate its training process. Both the intermediate layers from the teacher network and the injection layers from the student network are adaptively selected during training by evaluating a joint loss function in an iterative manner. This knowledge projection framework allows us to use crucial knowledge learned by large networks to guide the training of thinner student networks, avoiding over-fitting, achieving better network performance, and significantly reducing the complexity. Extensive experimental results on benchmark datasets have demonstrated that our proposed knowledge projection approach outperforms existing methods, improving accuracy by up to 4% while reducing network complexity by 4 to 10 times, which is very attractive for practical applications of deep neural networks.

Chiara Zizza, Adam Starr, Devin Hudson et al.

Virtual Learning Environments (VLEs) are spaces designed to educate students remotely via online platforms. Although traditional VLEs such as iSocial have shown promise in educating students, they offer limited immersion that diminishes learning effectiveness. This paper outlines a virtual reality learning environment (VRLE) over a high-speed network, which promotes educational effectiveness and efficiency via our creation of flexible content and infrastructure which meet established VLE standards with improved immersion. This paper further describes our implementation of multiple learning modules developed in High Fidelity, a "social VR" platform. Our experiment results show that the VR mode of content delivery better stimulates the generalization of lessons to the real world than non-VR lessons and provides improved immersion when compared to an equivalent desktop version.

Guanghan Ning, Zhi Zhang, Zhihai He

Human pose estimation using deep neural networks aims to map input images with large variations into multiple body keypoints which must satisfy a set of geometric constraints and inter-dependency imposed by the human body model. This is a very challenging nonlinear manifold learning process in a very high dimensional feature space. We believe that the deep neural network, which is inherently an algebraic computation system, is not the most effecient way to capture highly sophisticated human knowledge, for example those highly coupled geometric characteristics and interdependence between keypoints in human poses. In this work, we propose to explore how external knowledge can be effectively represented and injected into the deep neural networks to guide its training process using learned projections that impose proper prior. Specifically, we use the stacked hourglass design and inception-resnet module to construct a fractal network to regress human pose images into heatmaps with no explicit graphical modeling. We encode external knowledge with visual features which are able to characterize the constraints of human body models and evaluate the fitness of intermediate network output. We then inject these external features into the neural network using a projection matrix learned using an auxiliary cost function. The effectiveness of the proposed inception-resnet module and the benefit in guided learning with knowledge projection is evaluated on two widely used benchmarks. Our approach achieves state-of-the-art performance on both datasets.

Guanghan Ning, Zhi Zhang, Chen Huang et al.

In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking. Our recurrent convolutional network exploits the history of locations as well as the distinctive visual features learned by the deep neural networks. Inspired by recent bounding box regression methods for object detection, we study the regression capability of Long Short-Term Memory (LSTM) in the temporal domain, and propose to concatenate high-level visual features produced by convolutional networks with region information. In contrast to existing deep learning based trackers that use binary classification for region candidates, we use regression for direct prediction of the tracking locations both at the convolutional layer and at the recurrent unit. Our extensive experimental results and performance comparison with state-of-the-art tracking methods on challenging benchmark video tracking datasets shows that our tracker is more accurate and robust while maintaining low computational cost. For most test video sequences, our method achieves the best tracking performance, often outperforms the second best by a large margin.

Miao Sun, Tony X. Han, Zhihai He

Currently, the state-of-the-art image classification algorithms outperform the best available object detector by a big margin in terms of average precision. We, therefore, propose a simple yet principled approach that allows us to leverage object detection through image classification on supporting regions specified by a preliminary object detector. Using a simple bag-of- words model based image classification algorithm, we leveraged the performance of the deformable model objector from 35.9% to 39.5% in average precision over 20 categories on standard PASCAL VOC 2007 detection dataset.