115 citations · 165 across the 11 of their papers we have counts for
12 papers
Cumulative Spatial Knowledge Distillation for Vision Transformers
Borui Zhao, Renjie Song, Jiajun Liang
Distilling knowledge from convolutional neural networks (CNNs) is a double-edged sword for vision transformers (ViTs). It boosts the performance since the image-friendly local-indu…
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers
Siyuan Wei, Tianzhu Ye, Shen Zhang +2
Although vision transformers (ViTs) have shown promising results in various computer vision tasks recently, their high computational cost limits their practical applications. Previ…
DarkVisionNet: Low-Light Imaging via RGB-NIR Fusion with Deep Inconsistency Prior
Shuangping Jin, Bingbing Yu, Minhao Jing +3
RGB-NIR fusion is a promising method for low-light imaging. However, high-intensity noise in low-light images amplifies the effect of structure inconsistency between RGB-NIR images…
Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data
Yuhao Chen, Xin Tan, Borui Zhao +4
Semi-supervised learning (SSL) has attracted enormous attention due to its vast potential of mitigating the dependence on large labeled datasets. The latest methods (e.g., FixMatch…
SimpleDG: Simple Domain Generalization Baseline without Bells and Whistles
Zhi Lv, Bo Lin, Siyuan Liang +4
We present a simple domain generalization baseline, which wins second place in both the common context generalization track and the hybrid context generalization track respectively…
Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
Shichao Dong, Jin Wang, Renhe Ji +3
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection. We find that the stumbling block to their generalization is caused by…
Efficient One Pass Self-distillation with Zipf's Label Smoothing
Jiajun Liang, Linze Li, Zhaodong Bing +4
Self-distillation exploits non-uniform soft supervision from itself during training and improves performance without any runtime cost. However, the overhead during training is ofte…
Explaining Deepfake Detection by Analysing Image Matching
Shichao Dong, Jin Wang, Jiajun Liang +2
This paper aims to interpret how deepfake detection models learn artifact features of images when just supervised by binary labels. To this end, three hypotheses from the perspecti…
Decoupled Knowledge Distillation
Borui Zhao, Quan Cui, Renjie Song +2
State-of-the-art distillation methods are mainly based on distilling deep features from intermediate layers, while the significance of logit distillation is greatly overlooked. To…
Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective
Quan Cui, Bingchen Zhao, Zhao-Min Chen +5
This work simultaneously considers the discriminability and transferability properties of deep representations in the typical supervised learning task, i.e., image classification.…
Scene Text Recognition from Two-Dimensional Perspective
Minghui Liao, Jian Zhang, Zhaoyi Wan +5
Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem. Though achieving excellent performance,…
EAST: An Efficient and Accurate Scene Text Detector
Xinyu Zhou, Cong Yao, He Wen +4
Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging…