AI Paper Atlas

Research map / Continual learning / Class-incremental

Towards Non Co-occurrence Incremental Object Detection with Unlabeled In-the-Wild Data

Na Dong, Yongqiang Zhang, Mingli Ding, Gim Hee Lee

IJCV 2024 · Continual learning › Class-incremental · approach: Incremental object detection with replay · 31 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 R-CNN distillation loss (ablation)dual-teacher student · VOC 19+1mAP all (%): 62.9 -> 66.9Improved
add image-level RoI mask distillation loss (ablation)dual-teacher student · VOC 19+1mAP all (%): 62.9 -> 67.1Improved
add instance-level heatmap distillation loss (ablation)dual-teacher student · VOC 19+1mAP all (%): 62.9 -> 66.2Improved
add R-CNN distillation loss (ablation)dual-teacher student · VOC 19+1mAP novel (%): 35.3 -> 44.9Improved
add blind sampling strategy to the full distillation framework (ablation)dual-teacher student · VOC 19+1mAP all (%): 68.7 -> 70.2Improved
add all three distillation losses to pseudo-label training (ablation)dual-teacher student · VOC 19+1mAP all (%): 62.9 -> 70.2Improved
use in-the-wild data with category overlap instead of withoutOurs · VOC 19+1mAP all (%): 70.2 -> 72.2Improved
use in-the-wild data with category overlap instead of withoutOurs · VOC 10+10mAP all (%): 60.4 -> 59.9Hurt
use our method instead of Shmelkov without co-occurrenceincremental detector · VOC 19+1mAP all (%): 61.4 -> 72.2Improved
use our method instead of Shmelkov without co-occurrenceincremental detector · VOC 10+10mAP novel (%): 49.1 -> 62.2Improved
use our method instead of Shmelkov without co-occurrenceincremental detector · VOC 10+5+5 base classesmAP base (%): 59.0 -> 56.7Hurt
use Open Images as in-the-wild dataOurs · VOC 19+1mAP novel (%): 39.2 -> 48.6Improved

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