Research map / Detection and segmentation / Weakly supervised detection and segmentation
What Can Human Sketches Do for Object Detection?
Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Aneeshan Sain, Subhadeep Koley, Tao Xiang, Yi-Zhe Song
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 the proposed sketch-enabled detector instead of the strongest supervised baseline | Category-level object detection · PASCAL-VOC 2007 | AP_.5: 34.6 -> 49.3 | Improved |
| Use the proposed sketch-enabled detector instead of the strongest supervised baseline | Category-level object detection · MS-COCO | AP_.5: 15.0 -> 25.9 | Improved |
| Use the proposed sketch-enabled detector instead of the strongest supervised baseline | Fine-grained object detection · SketchyCOCO | AP_.5: 12.1 -> 17.1 | Improved |
| Replace RPN with selective search (ablation) | Proposed detector · SketchyCOCO | AP_.5: -1.3 | Hurt |
| Replace RPN with edge boxes (ablation) | Proposed detector · SketchyCOCO | AP_.5: -2.6 | Hurt |
| Increase refinement iterations from K=1 to K=2 (ablation) | Proposed detector · SketchyCOCO | AP_.5: +2.4 | Improved |
| Increase refinement iterations from K=2 to K=3 (ablation) | Proposed detector · SketchyCOCO | AP_.5: +1.1 | Improved |
| Increase refinement iterations from K=3 to K=4 (ablation) | Proposed detector · SketchyCOCO | AP_.5: -0.2 | Hurt |
| Remove photo-encoder supervision (ablation) | Proposed detector · SketchyCOCO | AP_.5: -4.5 | Hurt |
Closest papers by meaning
- SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction (NeurIPS 2023 · similarity 0.90)
- Sketch2Saliency: Learning To Detect Salient Objects From Human Drawings (CVPR 2023 · similarity 0.88)
- Doodle to Search: Practical Zero-Shot Sketch-Based Image Retrieval (CVPR 2019 · similarity 0.88)
- Scene-Level Sketch-Based Image Retrieval with Minimal Pairwise Supervision (AAAI 2023 · similarity 0.88)
- Open Vocabulary Semantic Scene Sketch Understanding (CVPR 2024 · similarity 0.87)
- How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval? (CVPR 2024 · similarity 0.86)
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.
