Papers › Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks

Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks

31 Mar 2022arXiv:2203.17030archive 2025-07-28

Da-Wei Zhou, Han-Jia Ye, Liang Ma, Di Xie, ShiLiang Pu, De-Chuan Zhan

New classes arise frequently in our ever-changing world, e.g., emerging topics in social media and new types of products in e-commerce. A model should recognize new classes and meanwhile maintain discriminability over old classes. Under severe circumstances, only limited novel instances are available to incrementally update the model. The task of recognizing few-shot new classes without forgetting old classes is called few-shot class-incremental learning (FSCIL). In this work, we propose a new paradigm for FSCIL based on meta-learning by LearnIng Multi-phase Incremental Tasks (LIMIT), which synthesizes fake FSCIL tasks from the base dataset. The data format of fake tasks is consistent with the `real' incremental tasks, and we can build a generalizable feature space for the unseen tasks through meta-learning. Besides, LIMIT also constructs a calibration module based on transformer, which calibrates the old class classifiers and new class prototypes into the same scale and fills in the semantic gap. The calibration module also adaptively contextualizes the instance-specific embedding with a set-to-set function. LIMIT efficiently adapts to new classes and meanwhile resists forgetting over old classes. Experiments on three benchmark datasets (CIFAR100, miniImageNet, and CUB200) and large-scale dataset, i.e., ImageNet ILSVRC2012 validate that LIMIT achieves state-of-the-art performance.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

zhoudw-zdw/TPAMI-Limit officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Class Incremental LearningFew-Shot Class-Incremental LearningIncremental LearningMeta-Learningclass-incremental learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Class-Incremental Learning CIFAR-100 LIMIT Average Accuracy 61.85 #7 of 11 Archive leaderboard report
Few-Shot Class-Incremental Learning CIFAR-100 LIMIT Last Accuracy 51.23 #7 of 11 Archive leaderboard report
Few-Shot Class-Incremental Learning mini-Imagenet LIMIT Average Accuracy 59.06 #8 of 12 Archive leaderboard report
Few-Shot Class-Incremental Learning mini-Imagenet LIMIT Last Accuracy 49.19 #8 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

BASE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections