123 citations · 221 across the 17 of their papers we have counts for
17 papers
Semi-Unified Sparse Dictionary Learning with Learnable Top-K LISTA and FISTA Encoders
Fengsheng Lin, Shengyi Yan, Trac Duy Tran
We present a semi-unified sparse dictionary learning framework that bridges the gap between classical sparse models and modern deep architectures. Specifically, the method integrat…
DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection
Sheng Yan, Cunhang fan, Hongyu Zhang +3
At a cocktail party, humans exhibit an impressive ability to direct their attention. The auditory attention detection (AAD) approach seeks to identify the attended speaker by analy…
AutoTaskFormer: Searching Vision Transformers for Multi-task Learning
Yang Liu, Shen Yan, Yuge Zhang +5
Vision Transformers have shown great performance in single tasks such as classification and segmentation. However, real-world problems are not isolated, which calls for vision tran…
Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks
Qingyan Meng, Mingqing Xiao, Shen Yan +3
Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. For training the non-differentiable SNN models, the backpropagation through time (B…
VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners
Shen Yan, Tao Zhu, Zirui Wang +5
We explore an efficient approach to establish a foundational video-text model. We present VideoCoCa that maximally reuses a pretrained image-text contrastive captioner (CoCa) model…
Soft Augmentation for Image Classification
Yang Liu, Shen Yan, Laura Leal-Taixé +2
Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. Th…
Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation
Qingyan Meng, Mingqing Xiao, Shen Yan +3
Spiking Neural Network (SNN) is a promising energy-efficient AI model when implemented on neuromorphic hardware. However, it is a challenge to efficiently train SNNs due to their n…
Deep AutoAugment
Yu Zheng, Zhi Zhang, Shen Yan +1
While recent automated data augmentation methods lead to state-of-the-art results, their design spaces and the derived data augmentation strategies still incorporate strong human p…
Multiview Transformers for Video Recognition
Shen Yan, Xuehan Xiong, Anurag Arnab +4
Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations. Although transformer…
NAS-Bench-x11 and the Power of Learning Curves
Shen Yan, Colin White, Yash Savani +1
While early research in neural architecture search (NAS) required extreme computational resources, the recent releases of tabular and surrogate benchmarks have greatly increased th…
CATE: Computation-aware Neural Architecture Encoding with Transformers
Shen Yan, Kaiqiang Song, Fei Liu +1
Recent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of architecture encodings in Neural Architecture Search (NAS). These encodings encode either structu…
Deep Learning in the Era of Edge Computing: Challenges and Opportunities
Mi Zhang, Faen Zhang, Nicholas D. Lane +5
The era of edge computing has arrived. Although the Internet is the backbone of edge computing, its true value lies at the intersection of gathering data from sensors and extractin…
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
Shen Yan, Yu Zheng, Wei Ao +2
Existing Neural Architecture Search (NAS) methods either encode neural architectures using discrete encodings that do not scale well, or adopt supervised learning-based methods to…
Improve Unsupervised Domain Adaptation with Mixup Training
Shen Yan, Huan Song, Nanxiang Li +2
Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent…
HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking
Shen Yan, Biyi Fang, Faen Zhang +4
The use of automatic methods, often referred to as Neural Architecture Search (NAS), in designing neural network architectures has recently drawn considerable attention. In this wo…
MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution
Taojiannan Yang, Sijie Zhu, Chen Chen +3
We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency tra…
Word-based Domain Adaptation for Neural Machine Translation
Shen Yan, Leonard Dahlmann, Pavel Petrushkov +2
In this paper, we empirically investigate applying word-level weights to adapt neural machine translation to e-commerce domains, where small e-commerce datasets and large out-of-do…