539 citations · 2k across the 53 of their papers we have counts for
54 papers
PENCIL: Deep Learning with Noisy Labels
Kun Yi, Guo-Hua Wang, Jianxin Wu
Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with n…
Training Vision Transformers with Only 2040 Images
Yun-Hao Cao, Hao Yu, Jianxin Wu
Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition. They achieve competitive results with CNNs but the lack of…
A Unified Pruning Framework for Vision Transformers
Hao Yu, Jianxin Wu
Recently, vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. Yet the high computational costs and training data requir…
Fine-Grained Image Analysis with Deep Learning: A Survey
Xiu-Shen Wei, Yi-Zhe Song, Oisin Mac Aodha +5
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. The…
Residual Attention: A Simple but Effective Method for Multi-Label Recognition
Ke Zhu, Jianxin Wu
Multi-label image recognition is a challenging computer vision task of practical use. Progresses in this area, however, are often characterized by complicated methods, heavy comput…
Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach
Zeren Sun, Yazhou Yao, Xiu-Shen Wei +5
Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets. Especially for fine-grained recognition, which targets at distingui…
Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection
Chen-Lin Zhang, Yin Li, Jianxin Wu
Modern deep learning models require large amounts of accurately annotated data, which is often difficult to satisfy. Hence, weakly supervised tasks, including weakly supervised obj…
A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications
Yun-Hao Cao, Jianxin Wu
This paper starts by revealing a surprising finding: without any learning, a randomly initialized CNN can localize objects surprisingly well. That is, a CNN has an inductive bias t…
Friends and Foes in Learning from Noisy Labels
Yifan Zhou, Yifan Ge, Jianxin Wu
Learning from examples with noisy labels has attracted increasing attention recently. But, this paper will show that the commonly used CIFAR-based datasets and the accuracy evaluat…
Rethinking Self-Supervised Learning: Small is Beautiful
Yun-Hao Cao, Jianxin Wu
Self-supervised learning (SSL), in particular contrastive learning, has made great progress in recent years. However, a common theme in these methods is that they inherit the learn…
Distilling Virtual Examples for Long-tailed Recognition
Yin-Yin He, Jianxin Wu, Xiu-Shen Wei
We tackle the long-tailed visual recognition problem from the knowledge distillation perspective by proposing a Distill the Virtual Examples (DiVE) method. Specifically, by treatin…
Mixup Without Hesitation
Hao Yu, Huanyu Wang, Jianxin Wu
Mixup linearly interpolates pairs of examples to form new samples, which is easy to implement and has been shown to be effective in image classification tasks. However, there are t…
Distilling Knowledge by Mimicking Features
Guo-Hua Wang, Yifan Ge, Jianxin Wu
Knowledge distillation (KD) is a popular method to train efficient networks ("student") with the help of high-capacity networks ("teacher"). Traditional methods use the teacher's s…
ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification
Fu Xiong, Yang Xiao, Zhiguo Cao +3
Face verification can be regarded as a 2-class fine-grained visual recognition problem. Enhancing the feature's discriminative power is one of the key problems to improve its perfo…
Learning Expectation of Label Distribution for Facial Age and Attractiveness Estimation
Bin-Bin Gao, Xin-Xin Liu, Hong-Yu Zhou +2
Facial attributes (\eg, age and attractiveness) estimation performance has been greatly improved by using convolutional neural networks. However, existing methods have an inconsist…
Rethinking the Route Towards Weakly Supervised Object Localization
Chen-Lin Zhang, Yun-Hao Cao, Jianxin Wu
Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels. Previous methods often try to utilize feature maps and classification weights to…
Neural Network Pruning with Residual-Connections and Limited-Data
Jian-Hao Luo, Jianxin Wu
Filter level pruning is an effective method to accelerate the inference speed of deep CNN models. Although numerous pruning algorithms have been proposed, there are still two open…
Neural Random Subspace
Yun-Hao Cao, Jianxin Wu, Hanchen Wang +1
The random subspace method, known as the pillar of random forests, is good at making precise and robust predictions. However, there is not a straightforward way yet to combine it w…
Repetitive Reprediction Deep Decipher for Semi-Supervised Learning
Guo-Hua Wang, Jianxin Wu
Most recent semi-supervised deep learning (deep SSL) methods used a similar paradigm: use network predictions to update pseudo-labels and use pseudo-labels to update network parame…
Deep Learning for Fine-Grained Image Analysis: A Survey
Xiu-Shen Wei, Jianxin Wu, Quan Cui
Computer vision (CV) is the process of using machines to understand and analyze imagery, which is an integral branch of artificial intelligence. Among various research areas of CV,…
Towards Real-Time Action Recognition on Mobile Devices Using Deep Models
Chen-Lin Zhang, Xin-Xin Liu, Jianxin Wu
Action recognition is a vital task in computer vision, and many methods are developed to push it to the limit. However, current action recognition models have huge computational co…
Probabilistic End-to-end Noise Correction for Learning with Noisy Labels
Kun Yi, Jianxin Wu
Deep learning has achieved excellent performance in various computer vision tasks, but requires a lot of training examples with clean labels. It is easy to collect a dataset with n…
When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasets
Hong-Yu Zhou, Avital Oliver, Jianxin Wu +1
Semi-Supervised Learning (SSL) has been proved to be an effective way to leverage both labeled and unlabeled data at the same time. Recent semi-supervised approaches focus on deep…
Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification
Xiu-Shen Wei, Chen-Lin Zhang, Lingqiao Liu +2
Vehicle re-identification is an important problem and becomes desirable with the rapid expansion of applications in video surveillance and intelligent transportation. By recalling…