AI Paper Atlas

Research map / Continual learning / Class-incremental

Balancing between Forgetting and Acquisition in Incremental Subpopulation Learning

Mingfu Liang, Jiahuan Zhou, Wei Wei, Ying Wu

ECCV 2022 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning · 10 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
replace cross-entropy with the margin-enforce loss when finetuning the last layer (ablation)last-layer finetuning · Entity-13 (13 steps, uneven)average top-1 accuracy on all subclasses (%): 55.23 -> 60.38Improved
add Stage-2 with a random alpha_t to the margin loss (ablation)margin-loss classifier · Entity-13 (13 steps, uneven)average top-1 accuracy on all subclasses (%): 60.38 -> 71.59Improved
add Stage-2 with fixed alpha_t = 1 to the margin loss (ablation)margin-loss classifier · Entity-13 (13 steps, uneven)average top-1 accuracy on all subclasses (%): 60.38 -> 75.24Improved
search alpha_t with the acquisition-minus-forgetting objective instead of fixed alpha_t = 1 (ablation)two-stage method · Entity-13 (13 steps, uneven)average top-1 accuracy on all subclasses (%): 75.24 -> 78.75Improved
search alpha_t with the objective instead of random alpha_t (ablation)two-stage method · Entity-13 (13 steps, uneven)average top-1 accuracy on all subclasses (%): 71.59 -> 78.75Improved
add Stage-2 alpha search to the margin loss: forgetting (ablation)two-stage method · Entity-13 (13 steps, uneven)average forgetting F13 (%): 29.48 -> 3.35Improved
use the full two-stage method instead of PASStwo-stage method vs PASS · Entity-13 (13 steps, uneven)average top-1 accuracy on all subclasses (%): 52.49 -> 78.75Improved
use the full two-stage method instead of PASStwo-stage method vs PASS · Entity-30 (15 steps, uneven)average top-1 accuracy on all subclasses (%): 39.75 -> 71.69Improved
use the full two-stage method instead of PASStwo-stage method vs PASS · Entity-30 (8 steps, uneven)average top-1 accuracy on all subclasses (%): 54.99 -> 72.14Improved
use the full two-stage method instead of PASS: unseen accuracy, 4 stepstwo-stage method vs PASS · Entity-30 (4 steps, even)accuracy on unseen subclasses (%): 64.50 -> 64.73No clear effect
use the full two-stage method instead of PASS: unseen accuracy, 5 stepstwo-stage method vs PASS · Entity-13 (5 steps, even)accuracy on unseen subclasses (%): 73.12 -> 72.02Hurt
use the full two-stage method instead of PASS: forgetting, 15 stepstwo-stage method vs PASS · Entity-30 (15 steps, uneven)average forgetting F15 (%): 58.27 -> 3.48Improved

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