1 code implementation • 10 May 2024 • ZhenLiang Ni, Xinghao Chen, Yingjie Zhai, Yehui Tang, Yunhe Wang
Specifically, it achieves $43. 6\%$ mIoU on ADE20K with only $4. 0$ GFLOPs, which is $0. 9\%$ and $2. 5\%$ mIoU better than SeaFormer and SegNeXt but with about $38. 0\%$ fewer GFLOPs.
1 code implementation • 10 May 2024 • Xiaowen Ma, ZhenLiang Ni, Xinghao Chen
Specifically, we employ the coarse masks obtained from the fixed prototypes as a guide to adjust the fixed prototype towards the center of the semantic and spatial domains in the test image.
1 code implementation • 11 Feb 2023 • ZhenLiang Ni, Fukui Yang, Shengzhao Wen, Gang Zhang
By distilling the global pixel relation, the student detector can learn the relation between foreground and background features, and avoid the difficulty of distilling features directly for the feature imbalance issue.