AI Paper Atlas

Research map / Continual learning / Class-incremental

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

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

TPAMI 2022 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 175 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add prototype-initialized classifier (ablation)fine-tuning baseline · CIFAR100 (FSCIL)final accuracy: 2.65 -> 46.98Improved
add meta-calibration module (transformer) (ablation)Prototype classifier · CIFAR100 (FSCIL)final accuracy: 46.98 -> 48.30Improved
add one-phase fake-incremental meta-training (ablation)Prototype + Calibration · CIFAR100 (FSCIL)final accuracy: 48.30 -> 50.01Improved
use two-phase instead of one-phase fake tasks (ablation)LIMIT · CIFAR100 (FSCIL)final accuracy: 50.01 -> 51.23Improved
use LIMIT fake-incremental task sampling instead of CEC PIL (ablation)CEC · CUB200 (FSCIL)final accuracy: 52.28 -> 53.01Improved
use LIMIT fake-incremental task sampling instead of CEC PIL (ablation)LIMIT · CUB200 (FSCIL)final accuracy: 56.37 -> 57.41Improved
use LIMIT fake-incremental task sampling instead of CEC PIL (ablation)LIMIT · CIFAR100 (FSCIL)final accuracy: 51.03 -> 51.23Improved
use AutoAug instead of BasicAug (ablation)LIMIT · CIFAR100 (FSCIL)final accuracy: 49.92 -> 51.23Improved
use AutoAug instead of BasicAug (ablation)LIMIT · CUB200 (FSCIL)final accuracy: 58.45 -> 57.41Hurt
use AutoAug instead of BasicAug (ablation)CEC · CUB200 (FSCIL)final accuracy: 52.28 -> 51.38Hurt
use AutoAug instead of BasicAug (ablation)CEC · miniImageNet (FSCIL)final accuracy: 47.63 -> 47.97Improved
replace CEC with LIMIT (multi-phase fake-task sampling plus transformer calibration)CEC · CUB200 (FSCIL)incremental-class accuracy: 33.9 -> 41.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy