Skip to yearly menu bar Skip to main content


Poster

Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer

Yuwen Tan · Qinhao Zhou · Xiang Xiang · Ke Wang · Yuchuan Wu · Yongbin Li

Arch 4A-E Poster #362
[ ]
Fri 21 Jun 10:30 a.m. PDT — noon PDT

Abstract:

Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit different parameter-efficient tuning (PET) methods within the context of continual learning. We observe that adapter tuning demonstrates superiority over prompt-based methods, even without parameter expansion in each learning session. Motivated by this, we propose incrementally tuning the shared adapter without imposing parameter update constraints, enhancing the learning capacity of the backbone. Additionally, we employ feature sampling from stored prototypes to retrain a unified classifier, further improving its performance. We estimate the semantic shift of old prototypes without access to past samples and update stored prototypes session by session. Our proposed method eliminates model expansion and avoids retaining any image samples. It surpasses previous pre-trained model-based CIL methods and demonstrates remarkable continual learning capabilities. Experimental results on five CIL benchmarks validate the effectiveness of our approach, achieving the state-of-the-art (SOTA) performance.

Live content is unavailable. Log in and register to view live content