57 citations · 242 across the 21 of their papers we have counts for
22 papers
EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
Yulin Wang, Yang Yue, Rui Lu +3
The superior performance of modern visual backbones usually comes with a costly training procedure. We contribute to this issue by generalizing the idea of curriculum learning beyo…
Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
Chaoqun Du, Yulin Wang, Shiji Song +1
Long-tailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples. Such imbalance issue considerably i…
Computation-efficient Deep Learning for Computer Vision: A Survey
Yulin Wang, Yizeng Han, Chaofei Wang +3
Over the past decade, deep learning models have exhibited considerable advancements, reaching or even exceeding human-level performance in a range of visual perception tasks. This…
Dynamic Perceiver for Efficient Visual Recognition
Yizeng Han, Dongchen Han, Zeyu Liu +7
Early exiting has become a promising approach to improving the inference efficiency of deep networks. By structuring models with multiple classifiers (exits), predictions for ``eas…
Adaptive Rotated Convolution for Rotated Object Detection
Yifan Pu, Yiru Wang, Zhuofan Xia +6
Rotated object detection aims to identify and locate objects in images with arbitrary orientation. In this scenario, the oriented directions of objects vary considerably across dif…
Deep Incubation: Training Large Models by Divide-and-Conquering
Zanlin Ni, Yulin Wang, Jiangwei Yu +3
Recent years have witnessed a remarkable success of large deep learning models. However, training these models is challenging due to high computational costs, painfully slow conver…
EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones
Yulin Wang, Yang Yue, Rui Lu +4
The superior performance of modern deep networks usually comes with a costly training procedure. This paper presents a new curriculum learning approach for the efficient training o…
AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition
Yulin Wang, Yang Yue, Xinhong Xu +6
Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e.g., allocating the majority of c…
Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation
Wenxuan Ma, Jinming Zhang, Shuang Li +3
Extensive studies on Unsupervised Domain Adaptation (UDA) have propelled the deployment of deep learning from limited experimental datasets into real-world unconstrained domains. M…
Glance and Focus Networks for Dynamic Visual Recognition
Gao Huang, Yulin Wang, Kangchen Lv +4
Spatial redundancy widely exists in visual recognition tasks, i.e., discriminative features in an image or video frame usually correspond to only a subset of pixels, while the rema…
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition
Yulin Wang, Yang Yue, Yuanze Lin +6
Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy. As a representative work, the adapt…
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
Yulin Wang, Rui Huang, Shiji Song +2
Vision Transformers (ViT) have achieved remarkable success in large-scale image recognition. They split every 2D image into a fixed number of patches, each of which is treated as a…
Adaptive Focus for Efficient Video Recognition
Yulin Wang, Zhaoxi Chen, Haojun Jiang +3
In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each…
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
Le Yang, Haojun Jiang, Ruojin Cai +4
Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. The recent proposed CondenseNet has shown that this mecha…
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
Shuang Li, Kaixiong Gong, Chi Harold Liu +3
Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the remaining minority classes…
Transferable Semantic Augmentation for Domain Adaptation
Shuang Li, Mixue Xie, Kaixiong Gong +3
Domain adaptation has been widely explored by transferring the knowledge from a label-rich source domain to a related but unlabeled target domain. Most existing domain adaptation a…
Dynamic Neural Networks: A Survey
Yizeng Han, Gao Huang, Shiji Song +3
Dynamic neural network is an emerging research topic in deep learning. Compared to static models which have fixed computational graphs and parameters at the inference stage, dynami…
Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
Yulin Wang, Zanlin Ni, Shiji Song +2
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint. This paper a…
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
Yulin Wang, Kangchen Lv, Rui Huang +3
The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and hig…
Regularizing Deep Networks with Semantic Data Augmentation
Yulin Wang, Gao Huang, Shiji Song +3
Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translati…
Meta-Semi: A Meta-learning Approach for Semi-supervised Learning
Yulin Wang, Jiayi Guo, Shiji Song +1
Deep learning based semi-supervised learning (SSL) algorithms have led to promising results in recent years. However, they tend to introduce multiple tunable hyper-parameters, maki…
Implicit Semantic Data Augmentation for Deep Networks
Yulin Wang, Xuran Pan, Shiji Song +3
In this paper, we propose a novel implicit semantic data augmentation (ISDA) approach to complement traditional augmentation techniques like flipping, translation or rotation. Our…