AI Paper Atlas

Research map / Continual learning / Class-incremental

Learnable Distribution Calibration for Few-Shot Class-Incremental Learning

Binghao Liu, Boyu Yang, Lingxi Xie, Ren Wang, Qi Chuan Tian, Qixiang Ye

TPAMI 2023 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 41 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 Gaussian sampler to baseline (ablation)LDC · CUB200accuracy (%): 51.86 -> 54.58Improved
add recurrent calibration module to Gaussian sampler (ablation)LDC · CUB200accuracy (%): 54.58 -> 61.58Improved
use KL divergence instead of EMD matching loss (ablation)LDC · CUB200accuracy (%): 59.21 -> 61.58Improved
use KL divergence instead of JS divergence (ablation)LDC · CUB200accuracy (%): 58.68 -> 61.58Improved
use KL divergence instead of Hellinger distance (ablation)LDC · CUB200accuracy (%): 58.32 -> 61.58Improved
use learned covariance mapping instead of empirical strategy (ablation)LDC · mini-ImageNetconvergence epoch: 312 -> 206Improved
use learned covariance mapping instead of empirical strategy (ablation)LDC · CIFAR100generalization accuracy: 27.55% -> 31.36%Improved
replace Free-Lunch with LDC on regular samplesFree-Lunch · mini-ImageNet FSCIL normal casesPD: 25.62 -> 22.51Improved
replace Free-Lunch with LDC on outlier few-shot samplesFree-Lunch · mini-ImageNet FSCIL outlier casesPD: 30.07 -> 25.32Improved
replace Free-Lunch with LDCFree-Lunch · CUB200 FSCILaccuracy last session (%): 55.68 -> 61.58Improved
replace Free-Lunch with LDC in regular few-shotFree-Lunch · CUB 5-way 1-shotaccuracy (%): 79.56 -> 81.51Improved
replace CEC with LDCCEC · mini-ImageNet FSCILaccuracy last session (%): 47.63% -> 54.46%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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