arXiv subjects

Yan Yan

Publications and source records attributed to Yan Yan.

At least 181 records · Page 10Linked to original sources

arXiv2022

Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes

Real-time semantic segmentation, which aims to achieve high segmentation accuracy at real-time inference speed, has received substantial attention over the past few years. However, many state-of-the-art real-time semantic segmentation methods tend to sacrifice some spatial details or contextual information for fast inference, thus leading to degradation in segmentation quality. In this paper, we propose a novel Deep Multi-branch Aggregation Network (called DMA-Net) based on the encoder-decoder structure to perform real-time semantic segmentation in street scenes. Specifically, we first adopt ResNet-18 as the encoder to efficiently generate various levels of feature maps from different stages of convolutions. Then, we develop a Multi-branch Aggregation Network (MAN) as the decoder to effectively aggregate different levels of feature maps and capture the multi-scale information. In MAN, a lattice enhanced residual block is designed to enhance feature representations of the network by taking advantage of the lattice structure. Meanwhile, a feature transformation block is introduced to explicitly transform the feature map from the neighboring branch before feature aggregation. Moreover, a global context block is used to exploit the global contextual information. These key components are tightly combined and jointly optimized in a unified network. Extensive experimental results on the challenging Cityscapes and CamVid datasets demonstrate that our proposed DMA-Net respectively obtains 77.0% and 73.6% mean Intersection over Union (mIoU) at the inference speed of 46.7 FPS and 119.8 FPS by only using a single NVIDIA GTX 1080Ti GPU. This shows that DMA-Net provides a good tradeoff between segmentation quality and speed for semantic segmentation in street scenes.

cs.CV↗

arXiv2022

Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognition

Action recognition has been a heated topic in computer vision for its wide application in vision systems. Previous approaches achieve improvement by fusing the modalities of the skeleton sequence and RGB video. However, such methods have a dilemma between the accuracy and efficiency for the high complexity of the RGB video network. To solve the problem, we propose a multi-modality feature fusion network to combine the modalities of the skeleton sequence and RGB frame instead of the RGB video, as the key information contained by the combination of skeleton sequence and RGB frame is close to that of the skeleton sequence and RGB video. In this way, the complementary information is retained while the complexity is reduced by a large margin. To better explore the correspondence of the two modalities, a two-stage fusion framework is introduced in the network. In the early fusion stage, we introduce a skeleton attention module that projects the skeleton sequence on the single RGB frame to help the RGB frame focus on the limb movement regions. In the late fusion stage, we propose a cross-attention module to fuse the skeleton feature and the RGB feature by exploiting the correlation. Experiments on two benchmarks NTU RGB+D and SYSU show that the proposed model achieves competitive performance compared with the state-of-the-art methods while reduces the complexity of the network.

cs.CV↗

arXiv2022

Towards the Maximum Traffic Demand and Throughput Supported by Relay-Assisted mmWave Backhaul Networks

This paper investigates the throughput performance issue of the relay-assisted mmWave backhaul network. The maximum traffic demand of small-cell base stations (BSs) and the maximum throughput at the macro-cell BS have been found in a tree-style backhaul network through linear programming under different network settings, which concern both the number of radio chains available on BSs and the interference relationship between logical links in the backhaul network. A novel interference model for the relay-assisted mmWave backhaul network in the dense urban environment is proposed, which demonstrates the limited interference footprint of mmWave directional communications. Moreover, a scheduling algorithm is developed to find the optimal scheduling for tree-style mmWave backhaul networks. Extensive numerical analysis and simulations are conducted to show and validate the network throughput performance and the scheduling algorithm.

cs.NI↗

arXiv2022

An efficient distributed scheduling algorithm for relay-assisted mmWave backhaul networks

In this paper, a novel distributed scheduling algorithm is proposed, which aims to efficiently schedule both the uplink and downlink backhaul traffic in the relay-assisted mmWave backhaul network with a tree topology. The handshaking of control messages, calculation of local schedules, and the determination of final valid schedule are all discussed. Simulation results show that the performance of the distributed algorithm can reach very close to the maximum traffic demand of the backhaul network, and it can also adapt to the dynamic traffic with sharp traffic demand change of small-cell BSs quickly and accurately.

cs.NI↗

arXiv2022

Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning

With the remarkable success of deep learning recently, efficient network compression algorithms are urgently demanded for releasing the potential computational power of edge devices, such as smartphones or tablets. However, optimal network pruning is a non-trivial task which mathematically is an NP-hard problem. Previous researchers explain training a pruned network as buying a lottery ticket. In this paper, we investigate the Magnitude-Based Pruning (MBP) scheme and analyze it from a novel perspective through Fourier analysis on the deep learning model to guide model designation. Besides explaining the generalization ability of MBP using Fourier transform, we also propose a novel two-stage pruning approach, where one stage is to obtain the topological structure of the pruned network and the other stage is to retrain the pruned network to recover the capacity using knowledge distillation from lower to higher on the frequency domain. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate the superiority of our novel Fourier analysis based MBP compared to other traditional MBP algorithms.

cs.CV↗

arXiv2022

When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework

Human emotions involve basic and compound facial expressions. However, current research on facial expression recognition (FER) mainly focuses on basic expressions, and thus fails to address the diversity of human emotions in practical scenarios. Meanwhile, existing work on compound FER relies heavily on abundant labeled compound expression training data, which are often laboriously collected under the professional instruction of psychology. In this paper, we study compound FER in the cross-domain few-shot learning setting, where only a few images of novel classes from the target domain are required as a reference. In particular, we aim to identify unseen compound expressions with the model trained on easily accessible basic expression datasets. To alleviate the problem of limited base classes in our FER task, we propose a novel Emotion Guided Similarity Network (EGS-Net), consisting of an emotion branch and a similarity branch, based on a two-stage learning framework. Specifically, in the first stage, the similarity branch is jointly trained with the emotion branch in a multi-task fashion. With the regularization of the emotion branch, we prevent the similarity branch from overfitting to sampled base classes that are highly overlapped across different episodes. In the second stage, the emotion branch and the similarity branch play a "two-student game" to alternately learn from each other, thereby further improving the inference ability of the similarity branch on unseen compound expressions. Experimental results on both in-the-lab and in-the-wild compound expression datasets demonstrate the superiority of our proposed method against several state-of-the-art methods.

cs.CV↗

arXiv2022

Incorporating Multiple Cluster Centers for Multi-Label Learning

Multi-label learning deals with the problem that each instance is associated with multiple labels simultaneously. Most of the existing approaches aim to improve the performance of multi-label learning by exploiting label correlations. Although the data augmentation technique is widely used in many machine learning tasks, it is still unclear whether data augmentation is helpful to multi-label learning. In this article, we propose to leverage the data augmentation technique to improve the performance of multi-label learning. Specifically, we first propose a novel data augmentation approach that performs clustering on the real examples and treats the cluster centers as virtual examples, and these virtual examples naturally embody the local label correlations and label importances. Then, motivated by the cluster assumption that examples in the same cluster should have the same label, we propose a novel regularization term to bridge the gap between the real examples and virtual examples, which can promote the local smoothness of the learning function. Extensive experimental results on a number of real-world multi-label datasets clearly demonstrate that our proposed approach outperforms the state-of-the-art counterparts.

cs.LG↗

arXiv2021

Expert and Crowd-Guided Affect Annotation and Prediction

We employ crowdsourcing to acquire time-continuous affective annotations for movie clips, and refine noisy models trained from these crowd annotations incorporating expert information within a Multi-task Learning (MTL) framework. We propose a novel \textbf{e}xpert \textbf{g}uided MTL (EG-MTL) algorithm, which minimizes the loss with respect to both crowd and expert labels to learn a set of weights corresponding to each movie clip for which crowd annotations are acquired. We employ EG-MTL to solve two problems, namely, \textbf{\texttt{P1}}: where dynamic annotations acquired from both experts and crowdworkers for the \textbf{Validation} set are used to train a regression model with audio-visual clip descriptors as features, and predict dynamic arousal and valence levels on 5--15 second snippets derived from the clips; and \textbf{\texttt{P2}}: where a classification model trained on the \textbf{Validation} set using dynamic crowd and expert annotations (as features) and static affective clip labels is used for binary emotion recognition on the \textbf{Evaluation} set for which only dynamic crowd annotations are available. Observed experimental results confirm the effectiveness of the EG-MTL algorithm, which is reflected via improved arousal and valence estimation for \textbf{\texttt{P1}}, and higher recognition accuracy for \textbf{\texttt{P2}}.

cs.MM↗

arXiv2021

Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation

Since we were babies, we intuitively develop the ability to correlate the input from different cognitive sensors such as vision, audio, and text. However, in machine learning, this cross-modal learning is a nontrivial task because different modalities have no homogeneous properties. Previous works discover that there should be bridges among different modalities. From neurology and psychology perspective, humans have the capacity to link one modality with another one, e.g., associating a picture of a bird with the only hearing of its singing and vice versa. Is it possible for machine learning algorithms to recover the scene given the audio signal? In this paper, we propose a novel Cascade Attention-Guided Residue GAN (CAR-GAN), aiming at reconstructing the scenes given the corresponding audio signals. Particularly, we present a residue module to mitigate the gap between different modalities progressively. Moreover, a cascade attention guided network with a novel classification loss function is designed to tackle the cross-modal learning task. Our model keeps the consistency in high-level semantic label domain and is able to balance two different modalities. The experimental results demonstrate that our model achieves the state-of-the-art cross-modal audio-visual generation on the challenging Sub-URMP dataset. Code will be available at https://github.com/tuffr5/CAR-GAN.

cs.CV↗

arXiv2021

Multi-Modal Interaction Graph Convolutional Network for Temporal Language Localization in Videos

This paper focuses on tackling the problem of temporal language localization in videos, which aims to identify the start and end points of a moment described by a natural language sentence in an untrimmed video. However, it is non-trivial since it requires not only the comprehensive understanding of the video and sentence query, but also the accurate semantic correspondence capture between them. Existing efforts are mainly centered on exploring the sequential relation among video clips and query words to reason the video and sentence query, neglecting the other intra-modal relations (e.g., semantic similarity among video clips and syntactic dependency among the query words). Towards this end, in this work, we propose a Multi-modal Interaction Graph Convolutional Network (MIGCN), which jointly explores the complex intra-modal relations and inter-modal interactions residing in the video and sentence query to facilitate the understanding and semantic correspondence capture of the video and sentence query. In addition, we devise an adaptive context-aware localization method, where the context information is taken into the candidate moments and the multi-scale fully connected layers are designed to rank and adjust the boundary of the generated coarse candidate moments with different lengths. Extensive experiments on Charades-STA and ActivityNet datasets demonstrate the promising performance and superior efficiency of our model.

cs.CV↗

arXiv2021

Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Neural Networks

Algorithmic bias is of increasing concern, both to the research community, and society at large. Bias in AI is more abstract and unintuitive than traditional forms of discrimination and can be more difficult to detect and mitigate. A clear gap exists in the current literature on evaluating the relative bias in the performance of multi-class classifiers. In this work, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the class-wise bias of two models in comparison to one another. By evaluating the performance of these new metrics and by demonstrating their practical application, we show that they can be used to measure fairness as well as bias. These demonstrations show that our metrics can address specific needs for measuring bias in multi-class classification.

cs.LG↗

arXiv2021

Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition

Human activity recognition (HAR) based on multi-modal approach has been recently shown to improve the accuracy performance of HAR. However, restricted computational resources associated with wearable devices, i.e., smartwatch, failed to directly support such advanced methods. To tackle this issue, this study introduces an end-to-end Vision-to-Sensor Knowledge Distillation (VSKD) framework. In this VSKD framework, only time-series data, i.e., accelerometer data, is needed from wearable devices during the testing phase. Therefore, this framework will not only reduce the computational demands on edge devices, but also produce a learning model that closely matches the performance of the computational expensive multi-modal approach. In order to retain the local temporal relationship and facilitate visual deep learning models, we first convert time-series data to two-dimensional images by applying the Gramian Angular Field ( GAF) based encoding method. We adopted ResNet18 and multi-scale TRN with BN-Inception as teacher and student network in this study, respectively. A novel loss function, named Distance and Angle-wised Semantic Knowledge loss (DASK), is proposed to mitigate the modality variations between the vision and the sensor domain. Extensive experimental results on UTD-MHAD, MMAct, and Berkeley-MHAD datasets demonstrate the effectiveness and competitiveness of the proposed VSKD model which can deployed on wearable sensors.

cs.MM↗

arXiv2021

Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification

Deep AUC Maximization (DAM) is a new paradigm for learning a deep neural network by maximizing the AUC score of the model on a dataset. Most previous works of AUC maximization focus on the perspective of optimization by designing efficient stochastic algorithms, and studies on generalization performance of large-scale DAM on difficult tasks are missing. In this work, we aim to make DAM more practical for interesting real-world applications (e.g., medical image classification). First, we propose a new margin-based min-max surrogate loss function for the AUC score (named as AUC min-max-margin loss or simply AUC margin loss for short). It is more robust than the commonly used AUC square loss, while enjoying the same advantage in terms of large-scale stochastic optimization. Second, we conduct extensive empirical studies of our DAM method on four difficult medical image classification tasks, namely (i) classification of chest x-ray images for identifying many threatening diseases, (ii) classification of images of skin lesions for identifying melanoma, (iii) classification of mammogram for breast cancer screening, and (iv) classification of microscopic images for identifying tumor tissue. Our studies demonstrate that the proposed DAM method improves the performance of optimizing cross-entropy loss by a large margin, and also achieves better performance than optimizing the existing AUC square loss on these medical image classification tasks. Specifically, our DAM method has achieved the 1st place on Stanford CheXpert competition on Aug. 31, 2020. To the best of our knowledge, this is the first work that makes DAM succeed on large-scale medical image datasets. We also conduct extensive ablation studies to demonstrate the advantages of the new AUC margin loss over the AUC square loss on benchmark datasets. The proposed method is implemented in our open-sourced library LibAUC (www.libauc.org).

cs.LG↗

arXiv2021

Lipschitz Continuity Guided Knowledge Distillation

Knowledge distillation has become one of the most important model compression techniques by distilling knowledge from larger teacher networks to smaller student ones. Although great success has been achieved by prior distillation methods via delicately designing various types of knowledge, they overlook the functional properties of neural networks, which makes the process of applying those techniques to new tasks unreliable and non-trivial. To alleviate such problem, in this paper, we initially leverage Lipschitz continuity to better represent the functional characteristic of neural networks and guide the knowledge distillation process. In particular, we propose a novel Lipschitz Continuity Guided Knowledge Distillation framework to faithfully distill knowledge by minimizing the distance between two neural networks' Lipschitz constants, which enables teacher networks to better regularize student networks and improve the corresponding performance. We derive an explainable approximation algorithm with an explicit theoretical derivation to address the NP-hard problem of calculating the Lipschitz constant. Experimental results have shown that our method outperforms other benchmarks over several knowledge distillation tasks (e.g., classification, segmentation and object detection) on CIFAR-100, ImageNet, and PASCAL VOC datasets.

cs.LG↗

arXiv2021

Cross-View Exocentric to Egocentric Video Synthesis

Cross-view video synthesis task seeks to generate video sequences of one view from another dramatically different view. In this paper, we investigate the exocentric (third-person) view to egocentric (first-person) view video generation task. This is challenging because egocentric view sometimes is remarkably different from the exocentric view. Thus, transforming the appearances across the two different views is a non-trivial task. Particularly, we propose a novel Bi-directional Spatial Temporal Attention Fusion Generative Adversarial Network (STA-GAN) to learn both spatial and temporal information to generate egocentric video sequences from the exocentric view. The proposed STA-GAN consists of three parts: temporal branch, spatial branch, and attention fusion. First, the temporal and spatial branches generate a sequence of fake frames and their corresponding features. The fake frames are generated in both downstream and upstream directions for both temporal and spatial branches. Next, the generated four different fake frames and their corresponding features (spatial and temporal branches in two directions) are fed into a novel multi-generation attention fusion module to produce the final video sequence. Meanwhile, we also propose a novel temporal and spatial dual-discriminator for more robust network optimization. Extensive experiments on the Side2Ego and Top2Ego datasets show that the proposed STA-GAN significantly outperforms the existing methods.

cs.CV↗

arXiv2021

Saying the Unseen: Video Descriptions via Dialog Agents

Current vision and language tasks usually take complete visual data (e.g., raw images or videos) as input, however, practical scenarios may often consist the situations where part of the visual information becomes inaccessible due to various reasons e.g., restricted view with fixed camera or intentional vision block for security concerns. As a step towards the more practical application scenarios, we introduce a novel task that aims to describe a video using the natural language dialog between two agents as a supplementary information source given incomplete visual data. Different from most existing vision-language tasks where AI systems have full access to images or video clips, which may reveal sensitive information such as recognizable human faces or voices, we intentionally limit the visual input for AI systems and seek a more secure and transparent information medium, i.e., the natural language dialog, to supplement the missing visual information. Specifically, one of the intelligent agents - Q-BOT - is given two semantic segmented frames from the beginning and the end of the video, as well as a finite number of opportunities to ask relevant natural language questions before describing the unseen video. A-BOT, the other agent who has access to the entire video, assists Q-BOT to accomplish the goal by answering the asked questions. We introduce two different experimental settings with either a generative (i.e., agents generate questions and answers freely) or a discriminative (i.e., agents select the questions and answers from candidates) internal dialog generation process. With the proposed unified QA-Cooperative networks, we experimentally demonstrate the knowledge transfer process between the two dialog agents and the effectiveness of using the natural language dialog as a supplement for incomplete implicit visions.

cs.CV↗

arXiv2021

Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation

In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic bias generated by AI is more abstract and unintuitive therefore more difficult to explain and mitigate. A clear gap exists in the current literature on evaluating and mitigating bias in pruned neural networks. In this work, we strive to tackle the challenging issues of evaluating, mitigating, and explaining induced bias in pruned neural networks. Our paper makes three contributions. First, we propose two simple yet effective metrics, Combined Error Variance (CEV) and Symmetric Distance Error (SDE), to quantitatively evaluate the induced bias prevention quality of pruned models. Second, we demonstrate that knowledge distillation can mitigate induced bias in pruned neural networks, even with unbalanced datasets. Third, we reveal that model similarity has strong correlations with pruning induced bias, which provides a powerful method to explain why bias occurs in pruned neural networks. Our code is available at https://github.com/codestar12/pruning-distilation-bias

cs.LG↗

arXiv2021

Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection

Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions. While plausible facial details are predicted, the models tend to over-depend on local color appearance and suffer from ambiguous noise. To address such problem, this paper presents a novel Learning to Aggregate and Personalize (LAP) framework for unsupervised robust 3D face modeling. Instead of using controlled environment, the proposed method implicitly disentangles ID-consistent and scene-specific face from unconstrained photo set. Specifically, to learn ID-consistent face, LAP adaptively aggregates intrinsic face factors of an identity based on a novel curriculum learning approach with relaxed consistency loss. To adapt the face for a personalized scene, we propose a novel attribute-refining network to modify ID-consistent face with target attribute and details. Based on the proposed method, we make unsupervised 3D face modeling benefit from meaningful image facial structure and possibly higher resolutions. Extensive experiments on benchmarks show LAP recovers superior or competitive face shape and texture, compared with state-of-the-art (SOTA) methods with or without prior and supervision.

cs.CV↗