CVJan 24, 2023

Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning

arXiv:2301.09964v142 citationsh-index: 12
Originality Incremental advance
AI Analysis

This work addresses the problem of learning novel classes with limited labeled data while avoiding forgetting in incremental learning, which is incremental as it adapts existing semi-supervised techniques to a specific task.

The paper tackles the adaptability issue of semi-supervised learning in Few-Shot Class-Incremental Learning (Semi-FSCIL) by proposing UaD-CE, a framework that uses class-balanced self-training and uncertainty-aware distillation to incorporate unlabeled data, achieving improved performance on three benchmark datasets.

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 catastrophically forgetting all encountered classes previously. Currently, semi-supervised learning technique that harnesses freely-available unlabeled data to compensate for limited labeled data can boost the performance in numerous vision tasks, which heuristically can be applied to tackle issues in FSCIL, i.e., the Semi-supervised FSCIL (Semi-FSCIL). So far, very limited work focuses on the Semi-FSCIL task, leaving the adaptability issue of semi-supervised learning to the FSCIL task unresolved. In this paper, we focus on this adaptability issue and present a simple yet efficient Semi-FSCIL framework named Uncertainty-aware Distillation with Class-Equilibrium (UaD-CE), encompassing two modules UaD and CE. Specifically, when incorporating unlabeled data into each incremental session, we introduce the CE module that employs a class-balanced self-training to avoid the gradual dominance of easy-to-classified classes on pseudo-label generation. To distill reliable knowledge from the reference model, we further implement the UaD module that combines uncertainty-guided knowledge refinement with adaptive distillation. Comprehensive experiments on three benchmark datasets demonstrate that our method can boost the adaptability of unlabeled data with the semi-supervised learning technique in FSCIL tasks.

Code Implementations1 repo
Foundations

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

Your Notes