Jiebo Luo, Yang Cao, Zheng-Jun Zha, Wei Zhai, Kai Zhu
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.
Non-exemplar class-incremental learning is to recognize both the old and new classes when old class samples cannot be saved. It is a challenging task since representation optimization and feature retention can only be achieved under supervision from new classes. To address this problem, we propose a novel self-sustaining representation expansion scheme. Our scheme consists of a structure reorganization strategy that fuses main-branch expansion and side-branch updating to maintain the old features, and a main-branch distillation scheme to transfer the invariant knowledge. Furthermore, a prototype selection mechanism is proposed to enhance the discrimination between the old and new classes by selectively incorporating new samples into the distillation process. Extensive experiments on three benchmarks demonstrate significant incremental performance, outperforming the state-of-the-art methods by a margin of 3%, 3% and 6%, respectively.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.06359")
get_code_for_paper("2203.06359")
have("2203.06359")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.06359.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.06359)
Connect an agent — have() is free.