AI Paper Atlas

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

Class-Agnostic Object Detection with Multi-modal Transformer

Muhammad Maaz, Hanoona Rasheed, Salman Khan, Fahad Shahbaz Khan, Rao Muhammad Anwer, Ming-Hsuan Yang

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 93 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 language branch (captions) during training (ablation)MAVL · COCOAP50: 34.4 -> 39.3Improved
add language branch (captions) during training (ablation)MDETR · Pascal VOCAP50: 59.7 -> 63.9Improved
add caption-based language structure to training (ablation)Deformable DETR / MAVL · Pascal VOCAP50: 16.2 -> 61.6Improved
add multi-scale deformable attention (MSDA) (ablation)MAVL · Pascal VOCAP50: 59.9 -> 65.0Improved
use combined detections from several text queries instead of 'all objects' (ablation)MAVL · COCOAP50: 33.3 -> 42.0Improved
drop the 'all small objects' query from combined detections (ablation)MAVL · Pascal VOC / KITTIAP50: 63.7 -> 68.6 (VOC); 48.2 -> 45.8 (KITTI)Mixed
use general text queries instead of category-wise queries (ablation)MAVL · Pascal VOCAP50: 61.7 -> 68.6Improved
use stronger backbone (E5 instead of ResNet-101) (ablation)MDETR · KitchenAP50: 38.4 -> 53.3Improved
use task-specific query instead of general query (ablation)MAVL · DUT-OMRONAP50: 67.0 -> 75.5Improved
use task-specific query instead of general query (ablation)MAVL · CHAMELEONAP50: 30.2 -> 36.2Improved
replace RPN pseudo-labels with MAVL proposals for unknownsORE · ORE Task 1R50 unknown: 14.4 -> 50.1Improved
replace Selective Search proposals with MAVL proposals in pretrainingDETReg · Pascal VOC 10%AP: 51.4 -> 58.8Improved

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