Few-Shot Class-Incremental Learning via Class-Aware Bilateral Distillation
Few-Shot Class-Incremental Learning (FSCIL) aims to continually learn novel classes based on only few training samples, which poses a more challenging task than the well-studied Class-Incremental Learning (CIL) due to data scarcity. While knowledge distillation, a prevailing technique in CIL, can alleviate the catastrophic forgetting of older classes by regularizing outputs between current and previous model, it fails to consider the overfitting risk of novel classes in FSCIL. To adapt the powerful distillation technique for FSCIL, we propose a novel distillation structure, by taking the unique challenge of overfitting into account. Concretely, we draw knowledge from two complementary teachers. One is the model trained on abundant data from base classes that carries rich general knowledge, which can be leveraged for easing the overfitting of current novel classes. The other is the updated model from last incremental session that contains the adapted knowledge of previous novel classes, which is used for alleviating their forgetting. To combine the guidances, an adaptive strategy conditioned on the class-wise semantic similarities is introduced. Besides, for better preserving base class knowledge when accommodating novel concepts, we adopt a two-branch network with an attention-based aggregation module to dynamically merge predictions from two complementary branches. Extensive experiments on 3 popular FSCIL datasets: mini-ImageNet, CIFAR100 and CUB200 validate the effectiveness of our method by surpassing existing works by a significant margin.
Code (1)
Tasks
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningGeneral KnowledgeIncremental LearningKnowledge DistillationNovel ConceptsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt
Few-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones. Existing FSCIL methods usually fine-tune the entire backbone, leading …
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningUncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning
Given a model well-trained with a large-scale base dataset, Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding overfitting, without catastrophi…
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning+1A New Benchmark for Few-Shot Class-Incremental Learning: Redefining the Upper Bound
Class-incremental learning (CIL) aims to continuously adapt to emerging classes while retaining knowledge of previously learned ones. Few-shot class-incremental learning (FSCIL) presents an even greater challenge which r…
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningCALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning
Few-Shot Class-Incremental Learning (FSCIL) defines a practical but challenging task where models are required to continuously learn novel concepts with only a few training samples. Due to data scarcity, existing FSCIL m…
class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning+1Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning
Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on increme…
Few-Shot Object DetectionKnowledge DistillationObjectobject-detection+2