Papers › Forward Compatible Few-Shot Class-Incremental Learning

Forward Compatible Few-Shot Class-Incremental Learning

14 Mar 2022CVPR 2022 1arXiv:2203.06953archive 2025-07-28

Da-Wei Zhou, Fu-Yun Wang, Han-Jia Ye, Liang Ma, ShiLiang Pu, De-Chuan Zhan

Novel classes frequently arise in our dynamically changing world, e.g., new users in the authentication system, and a machine learning model should recognize new classes without forgetting old ones. This scenario becomes more challenging when new class instances are insufficient, which is called few-shot class-incremental learning (FSCIL). Current methods handle incremental learning retrospectively by making the updated model similar to the old one. By contrast, we suggest learning prospectively to prepare for future updates, and propose ForwArd Compatible Training (FACT) for FSCIL. Forward compatibility requires future new classes to be easily incorporated into the current model based on the current stage data, and we seek to realize it by reserving embedding space for future new classes. In detail, we assign virtual prototypes to squeeze the embedding of known classes and reserve for new ones. Besides, we forecast possible new classes and prepare for the updating process. The virtual prototypes allow the model to accept possible updates in the future, which act as proxies scattered among embedding space to build a stronger classifier during inference. FACT efficiently incorporates new classes with forward compatibility and meanwhile resists forgetting of old ones. Extensive experiments validate FACT's state-of-the-art performance. Code is available at: https://github.com/zhoudw-zdw/CVPR22-Fact

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

zhoudw-zdw/cvpr22-fact 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 Learningclass-incremental learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Class-Incremental Learning CIFAR-100 FACT Average Accuracy 62.24 #6 of 11 Archive leaderboard report
Few-Shot Class-Incremental Learning CIFAR-100 FACT Last Accuracy 52.10 #6 of 11 Archive leaderboard report
Few-Shot Class-Incremental Learning mini-Imagenet FACT Average Accuracy 60.70 #7 of 12 Archive leaderboard report
Few-Shot Class-Incremental Learning mini-Imagenet FACT Last Accuracy 50.49 #7 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.

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