Selective Attention-based Modulation for Continual Learning
CoRR(2024)
摘要
We present SAM, a biologically-plausible selective attention-driven
modulation approach to enhance classification models in a continual learning
setting. Inspired by neurophysiological evidence that the primary visual cortex
does not contribute to object manifold untangling for categorization and that
primordial attention biases are still embedded in the modern brain, we propose
to employ auxiliary saliency prediction features as a modulation signal to
drive and stabilize the learning of a sequence of non-i.i.d. classification
tasks. Experimental results confirm that SAM effectively enhances the
performance (in some cases up to about twenty percent points) of
state-of-the-art continual learning methods, both in class-incremental and
task-incremental settings. Moreover, we show that attention-based modulation
successfully encourages the learning of features that are more robust to the
presence of spurious features and to adversarial attacks than baseline methods.
Code is available at: https://github.com/perceivelab/SAM.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要