Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning
The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framework, e.g., the discrepancy between classes of different tasks is not well learned (i.e., inter-task confusion, ITC), and certain priority is still given to the latest class batch (i.e., old-new confusion, ONC). We empirically validate the side effects of the two types of confusion. Meanwhile, a novel solution called Task Correlated Incremental Learning (TCIL) is proposed to encourage discriminative and fair feature utilization across tasks. TCIL performs a multi-level knowledge distillation to propagate knowledge learned from old tasks to the new one. It establishes information flow paths at both feature and logit levels, enabling the learning to be aware of old classes. Besides, attention mechanism and classifier re-scoring are applied to generate more fair classification scores. We conduct extensive experiments on CIFAR100 and ImageNet100 datasets. The results demonstrate that TCIL consistently achieves state-of-the-art accuracy. It mitigates both ITC and ONC, while showing advantages in battle with catastrophic forgetting even no rehearsal memory is reserved.
Code (1)
Tasks
class-incremental learningClass Incremental LearningIncremental LearningIncremental Learning on CIFAR100-B0(5steps of 20 classes)Knowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning
Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our analyses suggest that classification supervision alone does not sufficien…
class-incremental learningResolving Causal Confusion in Reinforcement Learning via Robust Exploration
A reinforcement learning agent must distinguish between spurious correlations and causal relationships in its environment in order to robustly achieve its goals. Contrary to popular belief, such cases of causal confusion…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
Multi-Task Learning (MTL) enables multiple tasks to be learned within a shared network, but differences in objectives across tasks can cause negative transfer, where the learning of one task degrades another task's perfo…
Multi-Task LearningRecurrent Network Models for Human Dynamics
We propose the Encoder-Recurrent-Decoder (ERD) model for recognition and prediction of human body pose in videos and motion capture. The ERD model is a recurrent neural network that incorporates nonlinear encoder and dec…
DecoderHuman DynamicsHuman Pose ForecastingOptical Flow Estimation+1Advancing Relation Extraction through Language Probing with Exemplars from Set Co-Expansion
Relation Extraction (RE) is a pivotal task in automatically extracting structured information from unstructured text. In this paper, we present a multi-faceted approach that integrates representative examples and through…
ClassificationRelationRelation ClassificationRelation Extraction