Research map / Detection and segmentation / Open-set and few-shot detection
One-Shot Object Detection with Co-Attention and Co-Excitation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 CoAE instead of CompNet | One-shot object detection on VOC · VOC 2007 test, unseen classes | mAP: 52.1 -> 63.8 | Helped |
| Use CoAE instead of SiamMask | One-shot object detection on COCO · COCO val 2017, unseen classes | AP50: 16.8 -> 22.0 | Helped |
| Use the full 1,000-class ImageNet pretraining set instead of the reduced 725-class set | CoAE · VOC 2007 test, unseen classes | mAP: 63.8 -> 68.2 | Helped |
| Add co-attention (non-local object proposals) (ablation) | CoAE with co-excitation and margin loss · VOC | mAP: 54.2 -> 57.0 | Helped |
| Add co-attention (non-local object proposals) (ablation) | CoAE with co-excitation and margin loss · COCO | AP50: 21.7 -> 23.6 | Helped |
| Add co-excitation (SCE) (ablation) | CoAE with co-attention and margin loss · VOC | mAP: 56.1 -> 57.0 | Helped |
| Add co-excitation (SCE) (ablation) | CoAE with co-attention and margin loss · COCO | AP50: 23.3 -> 23.6 | Helped |
| Add margin-based ranking loss (ablation) | CoAE with co-attention and co-excitation · VOC | mAP: 51.6 -> 57.0 | Helped |
| Add margin-based ranking loss (ablation) | CoAE with co-attention and co-excitation · COCO | AP50: 22.4 -> 23.6 | Helped |
| Add co-attention and co-excitation (ablation) | CoAE with margin loss · VOC | mAP: 49.8 -> 57.0 | Helped |
| Add co-attention and co-excitation (ablation) | CoAE with margin loss · COCO | AP50: 13.5 -> 23.6 | Helped |
Closest papers by meaning
- Adaptive Image Transformer for One-Shot Object Detection (CVPR 2021 · similarity 0.89)
- Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection (AAAI 2021 · similarity 0.86)
- Balanced and Hierarchical Relation Learning for One-Shot Object Detection (CVPR 2022 · similarity 0.86)
- Exploring Base-Class Suppression with Prior Guidance for Bias-Free One-Shot Object Detection (AAAI 2024 · similarity 0.85)
- Visual Consensus Prompting for Co-Salient Object Detection (CVPR 2025 · similarity 0.84)
- Plug and Play Active Learning for Object Detection (CVPR 2024 · similarity 0.84)
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.