Specifying What You Know or Not for Multi-Label Class-Incremental Learning
This work addresses catastrophic forgetting in multi-label incremental learning, an incremental advance for scenarios like image tagging with multiple labels per sample.
The paper tackles the problem of multi-label class-incremental learning, where existing methods struggle due to ambiguity between known and unknown knowledge, and proposes the HCP framework to specify this knowledge, achieving a 3.3% average accuracy improvement over previous state-of-the-art on MS-COCO without replay buffers.
Existing class incremental learning is mainly designed for single-label classification task, which is ill-equipped for multi-label scenarios due to the inherent contradiction of learning objectives for samples with incomplete labels. We argue that the main challenge to overcome this contradiction in multi-label class-incremental learning (MLCIL) lies in the model's inability to clearly distinguish between known and unknown knowledge. This ambiguity hinders the model's ability to retain historical knowledge, master current classes, and prepare for future learning simultaneously. In this paper, we target at specifying what is known or not to accommodate Historical, Current, and Prospective knowledge for MLCIL and propose a novel framework termed as HCP. Specifically, (i) we clarify the known classes by dynamic feature purification and recall enhancement with distribution prior, enhancing the precision and retention of known information. (ii) We design prospective knowledge mining to probe the unknown, preparing the model for future learning. Extensive experiments validate that our method effectively alleviates catastrophic forgetting in MLCIL, surpassing the previous state-of-the-art by 3.3% on average accuracy for MS-COCO B0-C10 setting without replay buffers.