Research map / Detection and segmentation / Open-set and few-shot detection
Zero-Shot Object Detection
Ankan Bansal, Karan Sikka, Gaurav Sharma, Rama Chellappa, Ajay Divakaran
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 a static background class (ablation) | baseline ZSD · MSCOCO | Recall@100 IoU 0.5: 22.14 -> 24.39 | Improved |
| add a static background class (ablation) | baseline ZSD · Visual Genome | Recall@100 IoU 0.5: 5.19 -> 4.09 | Hurt |
| add dense sampling of the embedding space with OpenImages (ablation) | baseline ZSD · MSCOCO | Recall@100 IoU 0.5: 22.14 -> 27.19 | Improved |
| add dense sampling of the embedding space with OpenImages (ablation) | baseline ZSD · Visual Genome | Recall@100 IoU 0.5: 5.19 -> 4.75 | Hurt |
| add latent assignment based (LAB) background modeling (ablation) | baseline ZSD · Visual Genome | Recall@100 IoU 0.5: 5.19 -> 5.40 | Improved |
| add latent assignment based (LAB) background modeling (ablation) | baseline ZSD · MSCOCO | Recall@100 IoU 0.5: 22.14 -> 20.52 | Hurt |
| use latent assignment of background boxes instead of a static background class (ablation) | SB · Visual Genome | Recall@100 IoU 0.5: 4.09 -> 5.40 | Improved |
| add a static background class, evaluated with only top 50 detections (ablation) | baseline ZSD · MSCOCO | Recall@50 IoU 0.5: 17.05 -> 23.16 | Improved |
| add a static background class, evaluated with all detections (ablation) | baseline ZSD · MSCOCO | Recall@All IoU 0.5: 24.47 -> 25.12 | Improved |
| add LAB, evaluated with only top 50 detections (ablation) | baseline ZSD · Visual Genome | Recall@50 IoU 0.5: 3.68 -> 4.14 | Improved |
| add LAB, evaluated with all detections (ablation) | baseline ZSD · Visual Genome | Recall@All IoU 0.5: 6.45 -> 6.22 | Hurt |
| add dense sampling in generalized zero-shot detection (ablation) | baseline ZSD · MSCOCO GZSD | harmonic mean Recall@100: 11.67 -> 15.17 | Improved |
Closest papers by meaning
- Semantics-Guided Contrastive Network for Zero-Shot Object Detection (TPAMI 2022 · similarity 0.93)
- Meta-ZSDETR: Zero-shot DETR with Meta-learning (ICCV 2023 · similarity 0.93)
- Context-Aware Zero-Shot Learning for Object Recognition (ICML 2019 · similarity 0.93)
- Transductive Learning for Zero-Shot Object Detection (ICCV 2019 · similarity 0.92)
- Revisiting Few-Shot Object Detection with Vision-Language Models (NeurIPS 2024 · similarity 0.91)
- Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models (NeurIPS 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.
