Yibo Yang, Xiaojuan Qi, Jiaya Jia, Xiaoyang Wu, Jiequan Cui, Zhisheng Zhong, X. Zhang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for classification. In this paper, we explore the corresponding structures of the last-layer feature centers and classifiers in semantic segmentation. Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers. However, such a symmetric structure is beneficial to discrimination for the minor classes. To preserve these advantages, we introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure in imbalanced semantic segmentation. Experimental results show that our method can bring significant improvements on both 2D and 3D semantic segmentation benchmarks. Moreover, our method ranks 1 st and sets a new record (+6.8% mIoU) on the ScanNet200 test leaderboard.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2301.01100")
get_code_for_paper("2301.01100")
have("2301.01100")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2301.01100.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2301.01100)
Connect an agent — have() is free.