1 code implementation • ICCV 2023 • Zekang Zhang, Guangyu Gao, Jianbo Jiao, Chi Harold Liu, Yunchao Wei
However, most state-of-the-art methods use the freeze strategy for stability, which compromises the model's plasticity. In contrast, releasing parameter training for plasticity could lead to the best performance for all categories, but this requires discriminative feature representation. Therefore, we prioritize the model's plasticity and propose the Contrast inter- and intra-class representations for Incremental Segmentation (CoinSeg), which pursues discriminative representations for flexible parameter tuning.
1 code implementation • 13 Nov 2022 • Zekang Zhang, Guangyu Gao, Zhiyuan Fang, Jianbo Jiao, Yunchao Wei
Our MicroSeg is based on the assumption that background regions with strong objectness possibly belong to those concepts in the historical or future stages.
Class-Incremental Semantic Segmentation Continual Learning +1