AI Paper Atlas

Research map / Continual learning / Class-incremental

Class-Incremental Learning for Action Recognition in Videos

Jaeyoo Park, Minsoo Kang, Bohyung Han

ICCV 2021 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 62 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 time-channel importance map to the distillation loss (ablation)TCD · UCF101 (5x10 stages)average incremental accuracy (CNN): 71.21 -> 72.61Improved
add orthogonality loss to distillation without importance map (ablation)TCD · UCF101 (5x10 stages)average incremental accuracy (CNN): 71.21 -> 72.31Improved
add orthogonality loss on top of importance-map distillation (ablation)TCD · UCF101 (5x10 stages)average incremental accuracy (CNN): 72.61 -> 73.43Improved
add orthogonality loss on top of importance-map distillation (NME) (ablation)TCD · UCF101 (5x10 stages)average incremental accuracy (NME): 74.81 -> 75.35Improved
add orthogonality loss to distillation (ablation)TCD · UCF101 (10x5 stages, vs FT/EWC table)average incremental accuracy (CNN): 73.09 -> 74.89Improved
replace EWC with TCD distillationfine-tuning with exemplars · UCF101 (10x5 stages)average incremental accuracy (CNN): 69.70 -> 74.89Improved
increase memory per class from 1 to 10 (ablation)TCD · UCF101 (10 steps, memory budget)average incremental accuracy (CNN): 64.52 -> 76.66Improved
store all frames of each exemplar video rather than uniform sampling (ablation)TCD · UCF101 (10 steps, sampling)average incremental accuracy (CNN): 73.43 -> 73.89No clear effect
random frame sampling instead of uniform (ablation)TCD · UCF101 (10 steps, sampling)average incremental accuracy (CNN): 73.43 -> 73.17No clear effect
increase input frames from 8 to 16 (ablation)TCD · UCF101 (10 stages, frames)average incremental accuracy (CNN): 73.43 -> 75.17Improved
decrease input frames from 8 to 1 (ablation)TCD · UCF101 (10 stages, frames)average incremental accuracy (CNN): 73.43 -> 69.14Hurt
combine TCD distillation with BiCBiC · UCF101 (2x25 stages)average incremental accuracy (CNN): 68.85 -> 72.00Improved

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