AI Paper Atlas

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

Task-Agnostic Incremental Vision-Language Object Detection via Prompt Augmentation and Distribution-Aware Fusion

Yonghan Jiang, Zhengyuan Xie, Wenchu Liu, Linlan Huang, Fei Yang, Xialei Liu

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 0 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
replace static averaging with TTDF distribution-aware fusion (ablation)DitHub · ODinW-13 TA-IVLODAvg mAP: 32.5 -> 45.9Improved
add SPA on top of TTDF (ablation)TADA · ODinW-13 TA-IVLODAvg mAP: 45.9 -> 64.5Improved
combine learned classes with noise tokens in prompt augmentation versus noise tokens only (ablation)SPA · ODinW-13 TA-IVLODAvg mAP: 60.3 -> 64.5Improved
use synthetic noise tokens instead of COCO classes as distractors (ablation)SPA · ODinW-13 TA-IVLODZcoco mAP: 46.0 -> 47.4Improved
use Mahalanobis instead of Euclidean distance (ablation)TTDF · ODinW-13 TA-IVLODAvg mAP: 51.3 -> 64.5Improved
use Mahalanobis instead of Euclidean distance (ablation)TTDF · ODinW-13 TA-IVLODZcoco mAP: 45.9 -> 47.2Improved
add TADA to DitHub in standard IVLODDitHub · ODinW-13 standard IVLODAvg mAP: 66.3 -> 67.5Improved
add TADA to DitHub in TA-IVLODDitHub · ODinW-13 TA-IVLODAvg mAP: 32.5 -> 64.5Improved
add TADA in 10-shot TA-IVLODDitHub · ODinW-13 10-shot TA-IVLODAvgTA mAP: 30.3 -> 53.9Improved
add TADA versus GCD under conventional IODGCD · MS COCO IOD (40-40)mAP: 55.2 vs 54.5No clear effect
switch from single-task to cross-task promptsDitHub · ODinW-13Avg mAP: 66.3 -> 32.5Hurt

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