Research map / Detection and segmentation / CNN features
Adaptive Image Transformer for One-Shot Object Detection
Check 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 AIT instead of co-excitation to adapt proposal features to the query (ablation) | CoAE-style one-shot detector · PASCAL-VOC, unseen classes | mAP (%): 63.8 -> 70.9 | Helped |
| Add SCA to co-attention and AIT (ablation) | AIT configuration · PASCAL-VOC, unseen classes | mAP (%): 70.9 -> 71.3 | Helped |
| Use masked selective parallel attention in AIT (ablation) | AIT + SCA configuration · PASCAL-VOC, unseen classes | mAP (%): 71.3 -> 70.0 | Hurt |
| Use MCA instead of co-attention (ablation) | AIT + SCA configuration · PASCAL-VOC, unseen classes | mAP (%): 71.3 -> 72.2 | Helped |
| Use AIT-based method instead of CoAE | One-shot object detector · PASCAL-VOC 2007 test, unseen classes | mAP (%): 63.8 -> 72.2 | Helped |
| Use AIT-based method instead of CoAE | One-shot object detector · MS-COCO val 2017, unseen classes | average AP50 (%): 22.0 -> 24.3 | Helped |
| Use AIT-based method instead of CoAE | One-shot object detector · MS-COCO val 2017, seen classes | average AP50 (%): 40.9 -> 47.5 | Helped |
Closest papers by meaning
- Semantic-Aligned Fusion Transformer for One-Shot Object Detection (CVPR 2022 · similarity 0.89)
- One-Shot Object Detection with Co-Attention and Co-Excitation (NeurIPS 2019 · similarity 0.89)
- Training Object Detectors From Scratch: An Empirical Study in the Era of Vision Transformer (CVPR 2022 · similarity 0.88)
- Described Object Detection: Liberating Object Detection with Flexible Expressions (NeurIPS 2023 · similarity 0.88)
- Context-Transformer: Tackling Object Confusion for Few-Shot Detection (AAAI 2020 · similarity 0.88)
- Language-conditioned Detection Transformer (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.