AI Paper Atlas

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

Ceptor: Vision-Language Model-Infused Diverse Guidance for Detecting Anything

Jinyang Li, Bin-Bin Gao, Weifu Fu, Jingnan Luo, Hanqiu Deng, Yue Guo, Jun Liu, Yong Liu, Chengjie Wang, Wenbing Tao

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
add Infusion Strategies (ablation)Ceptor Visual-I · LVIS-minivalAPall: 57.5 -> 61.1Improved
add Infusion Strategies (ablation)Ceptor Visual-I · COCO-valAP: 61.0 -> 62.3Improved
add Harmonization Strategies (ablation)Ceptor Visual-G · COCO-valAP: 46.5 -> 48.1Improved
add Harmonization Strategies (ablation)Ceptor Text · COCO-valAP: 48.1 -> 50.2Improved
use VLM backbone instead of standard ViT (ablation)Ceptor Visual-I · LVIS-minivalAPall: 53.6 -> 61.1Improved
use VLM backbone instead of standard ViT (ablation)Ceptor Text · COCO-valAP: 49.1 -> 50.2Improved
use PRE instead of cross-attention for interactive prompts (ablation)Ceptor Visual-I · COCO-valAP: 59.3 -> 62.3Improved
use Ceptor PEcoreS instead of T-Rex2 Swin-TCeptor · Visual-I COCO-valAP: 56.6 -> 65.1Improved
use Ceptor PEcoreL instead of T-Rex2 Swin-LCeptor · Visual-I COCO-valAP: 58.5 -> 71.9Improved
use Ceptor PEcoreS instead of T-Rex2 Swin-TCeptor · Visual-G COCO-valAP: 38.8 -> 47.3Improved
use Ceptor PEcoreL instead of T-Rex2 Swin-LCeptor · Visual-G LVIS-valAPall: 45.3 -> 40.5Hurt
use Ceptor instead of T-Rex2 for hybrid promptsCeptor · Hybrid COCO-valAP: 42.5 -> 50.5Improved

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