Problem
Research questions and friction points this paper is trying to address.
class-incremental learning
multi-label scenarios
learning objectives contradiction
knowledge boundary ambiguity
Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning
🤖 AI Summary
本文针对多标签类增量学习中的知识保留和适应性问题，提出了一种强化的知识明确化框架KBK，通过特征提纯、不确定性处理及梯度补偿等方法提高模型性能。
📝 Abstract
Existing class-incremental learning methods struggle in multi-label scenarios (MLCIL) due to the inherent contradiction of learning objectives arising from co-occurring and incomplete labels. We argue that the core obstacle is the model's ambiguous boundary between known and unknown knowledge, which undermines historical knowledge retention, complicates current task learning, and limits adaptability to future concepts. To address this, we propose KBK (Knowing Beyond the Known), a reinforced knowledge specification framework that explicitly models what is known or not to unify historical, current, and prospective learning. Specifically, to clarify known knowledge, we develop a hierarchical feature purification module that disentangles fine-grained class-specific features from global features, where high-level semantic abstraction is reinforced with low-level visual features. Additionally, an uncertainty-aware recall enhancement strategy suppresses unreliable predictions based on distribution priors, improving the quality of historical recall. For probing the unknown, KBK leverages semantic correlations to synthesize informative unknown features under co-occurring, preserving embedding space for future learning. Furthermore, to mitigate heterogeneous forgetting, we design a category-balanced gradient compensation loss that dynamically reweights gradient backpropagation according to forgetting speeds. Experiments on multiple benchmarks validate the effectiveness and robustness of KBK, which surpasses prior best methods by 2.7% in Avg. Acc on MS-COCO B0-C10 setting even without any replay buffers.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Reinforced Knowledge Specification
Hierarchical Feature Purification
Uncertainty-Aware Recall Enhancement
Category-Balanced Gradient Compensation Loss
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
