163 citations · 1.6k across the 92 of their papers we have counts for
22 papers · 1 filter
Rethinking Supervised Pre-training for Better Downstream Transferring
Yutong Feng, Jianwen Jiang, Mingqian Tang +2
The pretrain-finetune paradigm has shown outstanding performance on many applications of deep learning, where a model is pre-trained on a upstream large dataset (e.g. ImageNet), an…
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
Tongkun Xu, Weihua Chen, Pichao Wang +3
Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to a different unlabeled target domain. Most existing UDA methods focus on lear…
Scaled ReLU Matters for Training Vision Transformers
Pichao Wang, Xue Wang, Hao Luo +5
Vision transformers (ViTs) have been an alternative design paradigm to convolutional neural networks (CNNs). However, the training of ViTs is much harder than CNNs, as it is sensit…
Graph Convolution for Re-ranking in Person Re-identification
Yuqi Zhang, Qian Qi, Chong Liu +4
Nowadays, deep learning is widely applied to extract features for similarity computation in person re-identification (re-ID) and have achieved great success. However, due to the no…
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
Xiaolong Ma, Minghai Qin, Fei Sun +7
Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation res…
KVT: k-NN Attention for Boosting Vision Transformers
Pichao Wang, Xue Wang, Fan Wang +4
Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transforme…