Research map / Detection and segmentation / Open-set and few-shot detection
Learning Object-Language Alignments for Open-Vocabulary Object Detection
Chuang Lin, Peize Sun, Yi Jiang, Ping Luo, Lizhen Qu, Gholamreza Haffari, Zehuan Yuan, Jianfei Cai
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 |
|---|---|---|---|
| Use one-to-one Hungarian region-word matching instead of one-to-many Sinkhorn matching (ablation) | VLDet region-word alignment · OV-COCO | novel mAP: +2.9 (29.1 to 32.0) | Improved |
| Use one-to-one Hungarian region-word matching instead of one-to-many Sinkhorn matching (ablation) | VLDet region-word alignment · OV-LVIS | mask novel AP: +3.2 (18.5 to 21.7) | Improved |
| Enlarge object vocabulary from category names to all caption nouns (ablation) | VLDet · OV-COCO | novel mAP: +1.8 (28.2 to 30.0) | Improved |
| Enlarge object vocabulary from category names to all caption nouns (ablation) | VLDet · OV-LVIS | mask novel AP: +1.5 (18.9 to 20.4) | Improved |
| Add image-text alignment loss to region-word loss (ablation) | VLDet · OV-COCO | novel mAP: +2.0 (30.0 to 32.0) | Improved |
| Add image-text alignment loss to region-word loss (ablation) | VLDet · OV-LVIS | mask novel AP: +1.3 (20.4 to 21.7) | Improved |
| Image-text loss alone without region-word loss (ablation) | VLDet · OV-COCO | novel mAP: -9.0 vs region-word only (21.0 vs 30.0) | Hurt |
| Bipartite matching (Hungarian) with region-word loss vs. max-score/max-size assignment (ablation) | VLDet region-word alignment · OV-COCO and OV-LVIS | novel mAP | Improved |
| Replace Faster R-CNN with VLDet bipartite matching on COCO Caption data vs. PB-OVD | VLDet · OV-COCO | novel AP: +1.2 (30.8 to 32.0) | Improved |
| Use Swin-B backbone instead of ResNet50 | VLDet · OV-LVIS | mask novel AP: +4.6 (21.7 to 26.3) | Improved |
| Transfer COCO-trained VLDet without retraining to PASCAL VOC and LVIS | VLDet · PASCAL VOC / LVIS transfer | box AP50: 61.7 vs 59.2 (PB-OVD) on VOC; 10.0 vs 8.0 on LVIS | Improved |
Closest papers by meaning
- Exploring Region-Word Alignment in Built-in Detector for Open-Vocabulary Object Detection (CVPR 2024 · similarity 0.94)
- Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection (NeurIPS 2022 · similarity 0.94)
- Explicit Semantic–Spatial Alignment for Open-Vocabulary Object Detection (ECCV 2026 · similarity 0.93)
- LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors (ICLR 2024 · similarity 0.91)
- Open-Det: An Efficient Learning Framework for Open-Ended Detection (ICML 2025 · similarity 0.91)
- Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection (ICLR 2025 · similarity 0.90)
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.
