Research map / Detection and segmentation / Open-set and few-shot detection
DetermiNet: A Large-Scale Diagnostic Dataset for Complex Visually-Grounded Referencing using Determiners
Clarence Lee, M Ganesh Kumar, Cheston Tan
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 |
|---|---|---|---|
| fine-tune MDETR on synthetic DetermiNet before real-image test | MDETR · Real images (100 COCO) | AP@IoU=0.5:0.95: 10.4 -> 19.5 | Improved |
| mask the determiner in the caption (ablation) | Oracle · DetermiNet test | AP@IoU=0.5:0.95: 93.5 -> 71.3 | Hurt |
| mask the determiner in the caption (ablation) | MDETR · DetermiNet test | AP@IoU=0.5:0.95: 70.6 -> 56.3 | Hurt |
| mask the noun in the caption (ablation) | Oracle · DetermiNet test | AP@IoU=0.5:0.95: 93.5 -> 11.3 | Hurt |
| replace perfect object detector with MDETR detections in oracle | Oracle · DetermiNet test | AP@IoU=0.5:0.95: 93.5 -> 62.8 | Hurt |
| increase training data per determiner from 10 to 1000 (ablation) | MDETR · DetermiNet test | AP@IoU=0.5:0.95: 2.8 -> 55.0 | Improved |
| increase training data per determiner from 10 to 1000 (ablation) | Oracle · DetermiNet test | AP@IoU=0.5:0.95: 17.9 -> 44.7 | Improved |
| use state-of-the-art grounding models without determiner schema constraints | MDETR · DetermiNet test | AP@IoU=0.5:0.95: 93.5 -> 70.6 | Hurt |
Closest papers by meaning
- GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation (CVPR 2026 · similarity 0.88)
- Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning (ICLR 2026 · similarity 0.88)
- Grounding Multimodal Large Language Models to the World (ICLR 2024 · similarity 0.87)
- RefDetector: A Simple Yet Effective Matching-based Method for Referring Expression Comprehension (AAAI 2025 · similarity 0.87)
- Referencing Where to Focus: Improving Visual Grounding with Referential Query (NeurIPS 2024 · similarity 0.87)
- Improved Visual Grounding through Self-Consistent Explanations (CVPR 2024 · similarity 0.87)
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.
