The following publications are possibly variants of this publication:
- A Bio-Inspired Light-Adaptive CMOS Vision Chip for Edge DetectionJae-Sung Kong, Sang-Ho Seo, Jung Hwan Kim, Jang-Kyoo Shin. vision 2005: 78-83
- An Attention-Based Token Pruning Method for Vision TransformersKaicheng Luo, Huaxiong Li, Xianzhong Zhou, Bing Huang. rskt 2022: 274-288 [doi]
- Dynamic Token Pruning in Plain Vision Transformers for Semantic SegmentationQuan Tang 0001, Bowen Zhang, Jiajun Liu, Fagui Liu, Yifan Liu. iccv 2023: 777-786 [doi]
- DynamicViT: Efficient Vision Transformers with Dynamic Token SparsificationYongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou 0001, Cho-Jui Hsieh. nips 2021: 13937-13949 [doi]
- No Token Left Behind: Efficient Vision Transformer via Dynamic Token IdlingXuwei Xu, Changlin Li, Yudong Chen 0002, Xiaojun Chang, Jiajun Liu, Sen Wang 0001. ausai 2024: 28-41 [doi]
- Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer InferenceJunyan Li, Li Lyna Zhang, Jiahang Xu, Yujing Wang, Shaoguang Yan, Yunqing Xia, YuQing Yang, Ting Cao, Hao Sun 0015, Weiwei Deng, Qi Zhang, Mao Yang. kdd 2023: 1280-1290 [doi]