AI Paper Atlas

Research map / Continual learning / Class-incremental

Label-Efficient Online Continual Object Detection in Streaming Video

Jay Zhangjie Wu, David Junhao Zhang, Wynne Hsu, Mengmi Zhang, Mike Zheng Shou

ICCV 2023 · Continual learning › Class-incremental · approach: Incremental object detection with replay · 21 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 Efficient-CLS (EMA slow learner + pseudo-labeling)iCaRL(our impl.) · EgoObjects (100% annotation)FAP: 60.80 -> 67.05Improved
add Efficient-CLSiCaRL(our impl.) · OAK (100% annotation)FAP: 36.14 -> 40.24Improved
add Efficient-CLS at 25% annotationDER++ · OAK (25% annotation)FAP: 37.79 -> 37.93Improved
add EMA slow learner (no pseudo-labeling) (ablation)iCaRL · OAK 6.25% annotationFAP: 23.04 -> 27.84Improved
add pseudo-labeling by the fast learner itself (no EMA) (ablation)iCaRL · OAK 12.5% annotationFAP: 28.76 -> 31.60Improved
add pseudo-labeling by the fast learner itself (no EMA) (ablation)iCaRL · OAK 12.5% annotationF (forgetting): -5.48 -> -4.83No clear effect
add slow-learner pseudo-labeling on top of EMA (ablation)iCaRL · OAK 25% annotationFAP: 34.79 -> 38.36Improved
add data augmentation on pseudo-labeled frames (ablation)Efficient-CLS · OAK 12.5% annotationFAP: 30.32 -> 33.92Improved
use class-balanced replay buffer instead of random store (ablation)Efficient-CLS · OAK (100% annotation)FAP: 26.23 -> 40.24Improved
add RPN loss in pseudo training (ablation)Efficient-CLS · OAK 12.5% annotationFAP: 33.92 -> 33.64No clear effect
raise pseudo-label confidence threshold from 0.1 to 0.7 (ablation)Efficient-CLS · OAK 12.5% annotationFAP: 30.33 -> 33.92Improved
raise pseudo loss weight from 1.0 to 4.0 (ablation)Efficient-CLS · OAK 12.5% annotationFAP: 33.92 -> 30.08Hurt

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