arXiv subjects

Yan Yan

Publications and source records attributed to Yan Yan.

At least 163 records · Page 9Linked to original sources

arXiv2022

MLP-GAN for Brain Vessel Image Segmentation

Brain vessel image segmentation can be used as a promising biomarker for better prevention and treatment of different diseases. One successful approach is to consider the segmentation as an image-to-image translation task and perform a conditional Generative Adversarial Network (cGAN) to learn a transformation between two distributions. In this paper, we present a novel multi-view approach, MLP-GAN, which splits a 3D volumetric brain vessel image into three different dimensional 2D images (i.e., sagittal, coronal, axial) and then feed them into three different 2D cGANs. The proposed MLP-GAN not only alleviates the memory issue which exists in the original 3D neural networks but also retains 3D spatial information. Specifically, we utilize U-Net as the backbone for our generator and redesign the pattern of skip connection integrated with the MLP-Mixer which has attracted lots of attention recently. Our model obtains the ability to capture cross-patch information to learn global information with the MLP-Mixer. Extensive experiments are performed on the public brain vessel dataset that show our MLP-GAN outperforms other state-of-the-art methods. We release our code at https://github.com/bxie9/MLP-GAN

eess.IV↗

arXiv2022

DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection

The prosperity of deep learning contributes to the rapid progress in scene text detection. Among all the methods with convolutional networks, segmentation-based ones have drawn extensive attention due to their superiority in detecting text instances of arbitrary shapes and extreme aspect ratios. However, the bottom-up methods are limited to the performance of their segmentation models. In this paper, we propose DPTNet (Dual-Path Transformer Network), a simple yet effective architecture to model the global and local information for the scene text detection task. We further propose a parallel design that integrates the convolutional network with a powerful self-attention mechanism to provide complementary clues between the attention path and convolutional path. Moreover, a bi-directional interaction module across the two paths is developed to provide complementary clues in the channel and spatial dimensions. We also upgrade the concentration operation by adding an extra multi-head attention layer to it. Our DPTNet achieves state-of-the-art results on the MSRA-TD500 dataset, and provides competitive results on other standard benchmarks in terms of both detection accuracy and speed.

cs.CV↗

arXiv2022

Progressive Cross-modal Knowledge Distillation for Human Action Recognition

Wearable sensor-based Human Action Recognition (HAR) has achieved remarkable success recently. However, the accuracy performance of wearable sensor-based HAR is still far behind the ones from the visual modalities-based system (i.e., RGB video, skeleton, and depth). Diverse input modalities can provide complementary cues and thus improve the accuracy performance of HAR, but how to take advantage of multi-modal data on wearable sensor-based HAR has rarely been explored. Currently, wearable devices, i.e., smartwatches, can only capture limited kinds of non-visual modality data. This hinders the multi-modal HAR association as it is unable to simultaneously use both visual and non-visual modality data. Another major challenge lies in how to efficiently utilize multimodal data on wearable devices with their limited computation resources. In this work, we propose a novel Progressive Skeleton-to-sensor Knowledge Distillation (PSKD) model which utilizes only time-series data, i.e., accelerometer data, from a smartwatch for solving the wearable sensor-based HAR problem. Specifically, we construct multiple teacher models using data from both teacher (human skeleton sequence) and student (time-series accelerometer data) modalities. In addition, we propose an effective progressive learning scheme to eliminate the performance gap between teacher and student models. We also designed a novel loss function called Adaptive-Confidence Semantic (ACS), to allow the student model to adaptively select either one of the teacher models or the ground-truth label it needs to mimic. To demonstrate the effectiveness of our proposed PSKD method, we conduct extensive experiments on Berkeley-MHAD, UTD-MHAD, and MMAct datasets. The results confirm that the proposed PSKD method has competitive performance compared to the previous mono sensor-based HAR methods.

cs.CV↗

arXiv2022

Seeing your sleep stage: cross-modal distillation from EEG to infrared video

It is inevitably crucial to classify sleep stage for the diagnosis of various diseases. However, existing automated diagnosis methods mostly adopt the "gold-standard" lectroencephalogram (EEG) or other uni-modal sensing signal of the PolySomnoGraphy (PSG) machine in hospital, that are expensive, importable and therefore unsuitable for point-of-care monitoring at home. To enable the sleep stage monitoring at home, in this paper, we analyze the relationship between infrared videos and the EEG signal and propose a new task: to classify the sleep stage using infrared videos by distilling useful knowledge from EEG signals to the visual ones. To establish a solid cross-modal benchmark for this application, we develop a new dataset termed as Seeing your Sleep Stage via Infrared Video and EEG ($S^3VE$). $S^3VE$ is a large-scale dataset including synchronized infrared video and EEG signal for sleep stage classification, including 105 subjects and 154,573 video clips that is more than 1100 hours long. Our contributions are not limited to datasets but also about a novel cross-modal distillation baseline model namely the structure-aware contrastive distillation (SACD) to distill the EEG knowledge to infrared video features. The SACD achieved the state-of-the-art performances on both our $S^3VE$ and the existing cross-modal distillation benchmark. Both the benchmark and the baseline methods will be released to the community. We expect to raise more attentions and promote more developments in the sleep stage classification and more importantly the cross-modal distillation from clinical signal/media to the conventional media.

cs.CV↗

arXiv2022

Learning Omnidirectional Flow in 360-degree Video via Siamese Representation

Optical flow estimation in omnidirectional videos faces two significant issues: the lack of benchmark datasets and the challenge of adapting perspective video-based methods to accommodate the omnidirectional nature. This paper proposes the first perceptually natural-synthetic omnidirectional benchmark dataset with a 360-degree field of view, FLOW360, with 40 different videos and 4,000 video frames. We conduct comprehensive characteristic analysis and comparisons between our dataset and existing optical flow datasets, which manifest perceptual realism, uniqueness, and diversity. To accommodate the omnidirectional nature, we present a novel Siamese representation Learning framework for Omnidirectional Flow (SLOF). We train our network in a contrastive manner with a hybrid loss function that combines contrastive loss and optical flow loss. Extensive experiments verify the proposed framework's effectiveness and show up to 40% performance improvement over the state-of-the-art approaches. Our FLOW360 dataset and code are available at https://siamlof.github.io/.

cs.CV↗

arXiv2022

Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problem

Several studies have recently pointed that existing Visual Question Answering (VQA) models heavily suffer from the language prior problem, which refers to capturing superficial statistical correlations between the question type and the answer whereas ignoring the image contents. Numerous efforts have been dedicated to strengthen the image dependency by creating the delicate models or introducing the extra visual annotations. However, these methods cannot sufficiently explore how the visual cues explicitly affect the learned answer representation, which is vital for language reliance alleviation. Moreover, they generally emphasize the class-level discrimination of the learned answer representation, which overlooks the more fine-grained instance-level patterns and demands further optimization. In this paper, we propose a novel collaborative learning scheme from the viewpoint of visual perturbation calibration, which can better investigate the fine-grained visual effects and mitigate the language prior problem by learning the instance-level characteristics. Specifically, we devise a visual controller to construct two sorts of curated images with different perturbation extents, based on which the collaborative learning of intra-instance invariance and inter-instance discrimination is implemented by two well-designed discriminators. Besides, we implement the information bottleneck modulator on latent space for further bias alleviation and representation calibration. We impose our visual perturbation-aware framework to three orthodox baselines and the experimental results on two diagnostic VQA-CP benchmark datasets evidently demonstrate its effectiveness. In addition, we also justify its robustness on the balanced VQA benchmark.

cs.CV↗

arXiv2022

Quantized GAN for Complex Music Generation from Dance Videos

We present Dance2Music-GAN (D2M-GAN), a novel adversarial multi-modal framework that generates complex musical samples conditioned on dance videos. Our proposed framework takes dance video frames and human body motions as input, and learns to generate music samples that plausibly accompany the corresponding input. Unlike most existing conditional music generation works that generate specific types of mono-instrumental sounds using symbolic audio representations (e.g., MIDI), and that usually rely on pre-defined musical synthesizers, in this work we generate dance music in complex styles (e.g., pop, breaking, etc.) by employing a Vector Quantized (VQ) audio representation, and leverage both its generality and high abstraction capacity of its symbolic and continuous counterparts. By performing an extensive set of experiments on multiple datasets, and following a comprehensive evaluation protocol, we assess the generative qualities of our proposal against alternatives. The attained quantitative results, which measure the music consistency, beats correspondence, and music diversity, demonstrate the effectiveness of our proposed method. Last but not least, we curate a challenging dance-music dataset of in-the-wild TikTok videos, which we use to further demonstrate the efficacy of our approach in real-world applications -- and which we hope to serve as a starting point for relevant future research.

cs.CV↗

arXiv2022

Network Binarization via Contrastive Learning

Neural network binarization accelerates deep models by quantizing their weights and activations into 1-bit. However, there is still a huge performance gap between Binary Neural Networks (BNNs) and their full-precision (FP) counterparts. As the quantization error caused by weights binarization has been reduced in earlier works, the activations binarization becomes the major obstacle for further improvement of the accuracy. BNN characterises a unique and interesting structure, where the binary and latent FP activations exist in the same forward pass (i.e., $\text{Binarize}(\mathbf{a}_F) = \mathbf{a}_B$). To mitigate the information degradation caused by the binarization operation from FP to binary activations, we establish a novel contrastive learning framework while training BNNs through the lens of Mutual Information (MI) maximization. MI is introduced as the metric to measure the information shared between binary and FP activations, which assists binarization with contrastive learning. Specifically, the representation ability of the BNNs is greatly strengthened via pulling the positive pairs with binary and FP activations from the same input samples, as well as pushing negative pairs from different samples (the number of negative pairs can be exponentially large). This benefits the downstream tasks, not only classification but also segmentation and depth estimation, etc. The experimental results show that our method can be implemented as a pile-up module on existing state-of-the-art binarization methods and can remarkably improve the performance over them on CIFAR-10/100 and ImageNet, in addition to the great generalization ability on NYUD-v2.

cs.CV↗

arXiv2022

Lipschitz Continuity Retained Binary Neural Network

Relying on the premise that the performance of a binary neural network can be largely restored with eliminated quantization error between full-precision weight vectors and their corresponding binary vectors, existing works of network binarization frequently adopt the idea of model robustness to reach the aforementioned objective. However, robustness remains to be an ill-defined concept without solid theoretical support. In this work, we introduce the Lipschitz continuity, a well-defined functional property, as the rigorous criteria to define the model robustness for BNN. We then propose to retain the Lipschitz continuity as a regularization term to improve the model robustness. Particularly, while the popular Lipschitz-involved regularization methods often collapse in BNN due to its extreme sparsity, we design the Retention Matrices to approximate spectral norms of the targeted weight matrices, which can be deployed as the approximation for the Lipschitz constant of BNNs without the exact Lipschitz constant computation (NP-hard). Our experiments prove that our BNN-specific regularization method can effectively strengthen the robustness of BNN (testified on ImageNet-C), achieving state-of-the-art performance on CIFAR and ImageNet.

cs.LG↗

arXiv2022

Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition

Most existing compound facial expression recognition (FER) methods rely on large-scale labeled compound expression data for training. However, collecting such data is labor-intensive and time-consuming. In this paper, we address the compound FER task in the cross-domain few-shot learning (FSL) setting, which requires only a few samples of compound expressions in the target domain. Specifically, we propose a novel cascaded decomposition network (CDNet), which cascades several learn-to-decompose modules with shared parameters based on a sequential decomposition mechanism, to obtain a transferable feature space. To alleviate the overfitting problem caused by limited base classes in our task, a partial regularization strategy is designed to effectively exploit the best of both episodic training and batch training. By training across similar tasks on multiple basic expression datasets, CDNet learns the ability of learn-to-decompose that can be easily adapted to identify unseen compound expressions. Extensive experiments on both in-the-lab and in-the-wild compound expression datasets demonstrate the superiority of our proposed CDNet against several state-of-the-art FSL methods. Code is available at: https://github.com/zouxinyi0625/CDNet.

cs.CV↗

arXiv2022

Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis

Despite the success of deep neural networks (DNNs) for real-world applications over time-series data such as mobile health, little is known about how to train robust DNNs for time-series domain due to its unique characteristics compared to images and text data. In this paper, we propose a novel algorithmic framework referred as RObust Training for Time-Series (RO-TS) to create robust DNNs for time-series classification tasks. Specifically, we formulate a min-max optimization problem over the model parameters by explicitly reasoning about the robustness criteria in terms of additive perturbations to time-series inputs measured by the global alignment kernel (GAK) based distance. We also show the generality and advantages of our formulation using the summation structure over time-series alignments by relating both GAK and dynamic time warping (DTW). This problem is an instance of a family of compositional min-max optimization problems, which are challenging and open with unclear theoretical guarantee. We propose a principled stochastic compositional alternating gradient descent ascent (SCAGDA) algorithm for this family of optimization problems. Unlike traditional methods for time-series that require approximate computation of distance measures, SCAGDA approximates the GAK based distance on-the-fly using a moving average approach. We theoretically analyze the convergence rate of SCAGDA and provide strong theoretical support for the estimation of GAK based distance. Our experiments on real-world benchmarks demonstrate that RO-TS creates more robust DNNs when compared to adversarial training using prior methods that rely on data augmentation or new definitions of loss functions. We also demonstrate the importance of GAK for time-series data over the Euclidean distance. The source code of RO-TS algorithms is available at https://github.com/tahabelkhouja/Robust-Training-for-Time-Series

cs.LG↗

arXiv2022

Unsupervised High-Resolution Portrait Gaze Correction and Animation

This paper proposes a gaze correction and animation method for high-resolution, unconstrained portrait images, which can be trained without the gaze angle and the head pose annotations. Common gaze-correction methods usually require annotating training data with precise gaze, and head pose information. Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels. To address this issue, we first create two new portrait datasets: CelebGaze and high-resolution CelebHQGaze. Second, we formulate the gaze correction task as an image inpainting problem, addressed using a Gaze Correction Module (GCM) and a Gaze Animation Module (GAM). Moreover, we propose an unsupervised training strategy, i.e., Synthesis-As-Training, to learn the correlation between the eye region features and the gaze angle. As a result, we can use the learned latent space for gaze animation with semantic interpolation in this space. Moreover, to alleviate both the memory and the computational costs in the training and the inference stage, we propose a Coarse-to-Fine Module (CFM) integrated with GCM and GAM. Extensive experiments validate the effectiveness of our method for both the gaze correction and the gaze animation tasks in both low and high-resolution face datasets in the wild and demonstrate the superiority of our method with respect to the state of the arts. Code is available at https://github.com/zhangqianhui/GazeAnimationV2

cs.CV↗

arXiv2022

Robust Audio-Visual Instance Discrimination via Active Contrastive Set Mining

The recent success of audio-visual representation learning can be largely attributed to their pervasive property of audio-visual synchronization, which can be used as self-annotated supervision. As a state-of-the-art solution, Audio-Visual Instance Discrimination (AVID) extends instance discrimination to the audio-visual realm. Existing AVID methods construct the contrastive set by random sampling based on the assumption that the audio and visual clips from all other videos are not semantically related. We argue that this assumption is rough, since the resulting contrastive sets have a large number of faulty negatives. In this paper, we overcome this limitation by proposing a novel Active Contrastive Set Mining (ACSM) that aims to mine the contrastive sets with informative and diverse negatives for robust AVID. Moreover, we also integrate a semantically-aware hard-sample mining strategy into our ACSM. The proposed ACSM is implemented into two most recent state-of-the-art AVID methods and significantly improves their performance. Extensive experiments conducted on both action and sound recognition on multiple datasets show the remarkably improved performance of our method.

cs.MM↗

arXiv2022

HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud

Place recognition or loop closure detection is one of the core components in a full SLAM system. In this paper, aiming at strengthening the relevancy of local neighboring points and the contextual dependency among global points simultaneously, we investigate the exploitation of transformer-based network for feature extraction, and propose a Hierarchical Transformer for Place Recognition (HiTPR). The HiTPR consists of four major parts: point cell generation, short-range transformer (SRT), long-range transformer (LRT) and global descriptor aggregation. Specifically, the point cloud is initially divided into a sequence of small cells by downsampling and nearest neighbors searching. In the SRT, we extract the local feature for each point cell. While in the LRT, we build the global dependency among all of the point cells in the whole point cloud. Experiments on several standard benchmarks demonstrate the superiority of the HiTPR in terms of average recall rate, achieving 93.71% at top 1% and 86.63% at top 1 on the Oxford RobotCar dataset for example.

cs.CV↗

arXiv2022

Cross-View Panorama Image Synthesis

In this paper, we tackle the problem of synthesizing a ground-view panorama image conditioned on a top-view aerial image, which is a challenging problem due to the large gap between the two image domains with different view-points. Instead of learning cross-view mapping in a feedforward pass, we propose a novel adversarial feedback GAN framework named PanoGAN with two key components: an adversarial feedback module and a dual branch discrimination strategy. First, the aerial image is fed into the generator to produce a target panorama image and its associated segmentation map in favor of model training with layout semantics. Second, the feature responses of the discriminator encoded by our adversarial feedback module are fed back to the generator to refine the intermediate representations, so that the generation performance is continually improved through an iterative generation process. Third, to pursue high-fidelity and semantic consistency of the generated panorama image, we propose a pixel-segmentation alignment mechanism under the dual branch discrimiantion strategy to facilitate cooperation between the generator and the discriminator. Extensive experimental results on two challenging cross-view image datasets show that PanoGAN enables high-quality panorama image generation with more convincing details than state-of-the-art approaches. The source code and trained models are available at \url{https://github.com/sswuai/PanoGAN}.

cs.CV↗

arXiv2022

Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition

The sensor-based human activity recognition (HAR) in mobile application scenarios is often confronted with sensor modalities variation and annotated data deficiency. Given this observation, we devised a graph-inspired deep learning approach toward the sensor-based HAR tasks, which was further used to build a deep transfer learning model toward giving a tentative solution for these two challenging problems. Specifically, we present a multi-layer residual structure involved graph convolutional neural network (ResGCNN) toward the sensor-based HAR tasks, namely the HAR-ResGCNN approach. Experimental results on the PAMAP2 and mHealth data sets demonstrate that our ResGCNN is effective at capturing the characteristics of actions with comparable results compared to other sensor-based HAR models (with an average accuracy of 98.18% and 99.07%, respectively). More importantly, the deep transfer learning experiments using the ResGCNN model show excellent transferability and few-shot learning performance. The graph-based framework shows good meta-learning ability and is supposed to be a promising solution in sensor-based HAR tasks.

cs.CV↗

arXiv2022

Topological EEG Nonlinear Dynamics Analysis for Emotion Recognition

Emotional recognition through exploring the electroencephalography (EEG) characteristics has been widely performed in recent studies. Nonlinear analysis and feature extraction methods for understanding the complex dynamical phenomena are associated with the EEG patterns of different emotions. The phase space reconstruction is a typical nonlinear technique to reveal the dynamics of the brain neural system. Recently, the topological data analysis (TDA) scheme has been used to explore the properties of space, which provides a powerful tool to think over the phase space. In this work, we proposed a topological EEG nonlinear dynamics analysis approach using the phase space reconstruction (PSR) technique to convert EEG time series into phase space, and the persistent homology tool explores the topological properties of the phase space. We perform the topological analysis of EEG signals in different rhythm bands to build emotion feature vectors, which shows high distinguishing ability. We evaluate the approach with two well-known benchmark datasets, the DEAP and DREAMER datasets. The recognition results achieved accuracies of 99.37% and 99.35% in arousal and valence classification tasks with DEAP, and 99.96%, 99.93%, and 99.95% in arousal, valence, and dominance classifications tasks with DREAMER, respectively. The performances are supposed to be outperformed current state-of-art approaches in DREAMER (improved by 1% to 10% depends on temporal length), while comparable to other related works evaluated in DEAP. The proposed work is the first investigation in the emotion recognition oriented EEG topological feature analysis, which brought a novel insight into the brain neural system nonlinear dynamics analysis and feature extraction.

eess.SP↗

arXiv2022

Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes

Over the past few years, deep convolutional neural network-based methods have made great progress in semantic segmentation of street scenes. Some recent methods align feature maps to alleviate the semantic gap between them and achieve high segmentation accuracy. However, they usually adopt the feature alignment modules with the same network configuration in the decoder and thus ignore the different roles of stages of the decoder during feature aggregation, leading to a complex decoder structure. Such a manner greatly affects the inference speed. In this paper, we present a novel Stage-aware Feature Alignment Network (SFANet) based on the encoder-decoder structure for real-time semantic segmentation of street scenes. Specifically, a Stage-aware Feature Alignment module (SFA) is proposed to align and aggregate two adjacent levels of feature maps effectively. In the SFA, by taking into account the unique role of each stage in the decoder, a novel stage-aware Feature Enhancement Block (FEB) is designed to enhance spatial details and contextual information of feature maps from the encoder. In this way, we are able to address the misalignment problem with a very simple and efficient multi-branch decoder structure. Moreover, an auxiliary training strategy is developed to explicitly alleviate the multi-scale object problem without bringing additional computational costs during the inference phase. Experimental results show that the proposed SFANet exhibits a good balance between accuracy and speed for real-time semantic segmentation of street scenes. In particular, based on ResNet-18, SFANet respectively obtains 78.1% and 74.7% mean of class-wise Intersection-over-Union (mIoU) at inference speeds of 37 FPS and 96 FPS on the challenging Cityscapes and CamVid test datasets by using only a single GTX 1080Ti GPU.

cs.CV↗