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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Infusion Strategies (ablation) | Ceptor Visual-I · LVIS-minival | APall: 57.5 -> 61.1 | Improved |
| add Infusion Strategies (ablation) | Ceptor Visual-I · COCO-val | AP: 61.0 -> 62.3 | Improved |
| add Harmonization Strategies (ablation) | Ceptor Visual-G · COCO-val | AP: 46.5 -> 48.1 | Improved |
| add Harmonization Strategies (ablation) | Ceptor Text · COCO-val | AP: 48.1 -> 50.2 | Improved |
| use VLM backbone instead of standard ViT (ablation) | Ceptor Visual-I · LVIS-minival | APall: 53.6 -> 61.1 | Improved |
| use VLM backbone instead of standard ViT (ablation) | Ceptor Text · COCO-val | AP: 49.1 -> 50.2 | Improved |
| use PRE instead of cross-attention for interactive prompts (ablation) | Ceptor Visual-I · COCO-val | AP: 59.3 -> 62.3 | Improved |
| use Ceptor PEcoreS instead of T-Rex2 Swin-T | Ceptor · Visual-I COCO-val | AP: 56.6 -> 65.1 | Improved |
| use Ceptor PEcoreL instead of T-Rex2 Swin-L | Ceptor · Visual-I COCO-val | AP: 58.5 -> 71.9 | Improved |
| use Ceptor PEcoreS instead of T-Rex2 Swin-T | Ceptor · Visual-G COCO-val | AP: 38.8 -> 47.3 | Improved |
| use Ceptor PEcoreL instead of T-Rex2 Swin-L | Ceptor · Visual-G LVIS-val | APall: 45.3 -> 40.5 | Hurt |
| use Ceptor instead of T-Rex2 for hybrid prompts | Ceptor · Hybrid COCO-val | AP: 42.5 -> 50.5 | Improved |
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.
- T-Rex2 — T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy (ECCV 2024) · better on 11 of 12 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
- Just a Few Glances: Open-Set Visual Perception with Image Prompt Paradigm (AAAI 2025 · similarity 0.90)
- Generative Region-Language Pretraining for Open-Ended Object Detection (CVPR 2024 · similarity 0.90)
- Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection (CVPR 2024 · similarity 0.89)
- DoGA: Enhancing Grounded Object Detection via Grouped Pre-Training with Attributes (AAAI 2025 · similarity 0.89)
- CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection (AAAI 2025 · similarity 0.89)
- Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection (NeurIPS 2025 · similarity 0.89)
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.
