AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Self-Supervised Object Detection from Egocentric Videos

Peri Akiva, Jing Huang, Kevin J Liang, Rama Kovvuri, Xingyu Chen, Matt Feiszli, Kristin Dana, Tal Hassner

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 5 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
train DEVI on egocentric Ego4D frames instead of exocentric YouTubeBB-8M frames (ablation)DEVI · Ego4D valAP50: +3.86% AP50, +1.42% AR1, +8.80% AR10, +16.17% AR100Improved
replace Object Residual Module with K-Means clustering on raw features (ablation)DEVI · Ego4D valAP50Hurt
add multi-view loss with the Object Residual Module (ablation)DEVI · Ego4D valAP50: +1.62% AP50 over baselineImproved
add scale-regression loss on top of multi-view loss and ORM (ablation)DEVI · Ego4D valAP50: final AP50 6.51Improved
use DEVI end-to-end single-stage training instead of multi-stage FreeSOLOclass-agnostic detection · Ego4D valAR100: 17.00 -> 22.03 with about 72h -> 36h trainingImproved
DEVI versus FreeSOLO on lower-complexity EgoObjectsDEVI · EgoObjects valAP50 and AR1: AP50 14.96 vs 15.70; AR1 6.47 vs 8.30; AR100 39.43 vs 32.90Mixed
apply DEVI trained on Ego4D to COCO without any COCO trainingDEVI · COCO valAP50: AP50 8.03 vs FreeSOLO 12.20; AR100 25.93 vs 15.30Mixed

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