LGJan 23, 2025

Towards Robust Incremental Learning under Ambiguous Supervision

arXiv:2501.13584v4h-index: 17IJCAI
Originality Highly original
AI Analysis

This addresses the challenge of expensive data annotation in dynamic learning systems for incremental learning applications, representing a novel weakly-supervised paradigm.

The paper tackles the problem of incremental learning with ambiguous supervision by proposing Incremental Partial Label Learning (IPLL) and the Prototype-Guided Disambiguation and Replay Algorithm (PGDR), which achieves superior performance in disambiguation and reduces forgetting in experiments.

Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality annotated data in a dynamic learning system can be extremely expensive. To mitigate this problem, we propose a novel weakly-supervised learning paradigm called Incremental Partial Label Learning (IPLL), where the sequentially arrived data relate to a set of candidate labels rather than the ground truth. Technically, we develop the Prototype-Guided Disambiguation and Replay Algorithm (PGDR) which leverages the class prototypes as a proxy to mitigate two intertwined challenges in IPLL, i.e., label ambiguity and catastrophic forgetting. To handle the former, PGDR encapsulates a momentum-based pseudo-labeling algorithm along with prototype-guided initialization, resulting in a balanced perception of classes. To alleviate forgetting, we develop a memory replay technique that collects well-disambiguated samples while maintaining representativeness and diversity. By jointly distilling knowledge from curated memory data, our framework exhibits a great disambiguation ability for samples of new tasks and achieves less forgetting of knowledge. Extensive experiments demonstrate that PGDR achieves superior

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes