3 papers
cs.CV2023
ViT-Calibrator: Decision Stream Calibration for Vision Transformer
Lin Chen, Zhijie Jia, Tian Qiu +4
A surge of interest has emerged in utilizing Transformers in diverse vision tasks owing to its formidable performance. However, existing approaches primarily focus on optimizing in…
cs.CV2023
Life Regression based Patch Slimming for Vision Transformers
Jiawei Chen, Lin Chen, Jiang Yang +4
Vision transformers have achieved remarkable success in computer vision tasks by using multi-head self-attention modules to capture long-range dependencies within images. However,…
cs.CV2023
Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning
Wenxiang Xu, Yongcheng Jing, Linyun Zhou +4
The problem of deep long-tailed learning, a prevalent challenge in the realm of generic visual recognition, persists in a multitude of real-world applications. To tackle the heavil…