Research map / Detection and segmentation / CNN features
Cascade-DETR: Delving into High-Quality Universal Object Detection
Mingqiao Ye, Lei Ke, Siyuan Li, Yu-Wing Tai, Chi-Keung Tang, Martin Danelljan, Fisher Yu
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 cascade attention to DN-DETR (ablation) | DN-Def-DETR R50 · Cityscapes | AP: 19.0 -> 28.9 | Improved |
| add cascade attention to DN-DETR (ablation) | DN-Def-DETR R50 · UVO | AP: 22.3 -> 26.0 | Improved |
| add IoU-aware query recalibration to DN-DETR (ablation) | DN-Def-DETR R50 · UVO | AP: 22.3 -> 25.9 | Improved |
| combine cascade attention with query recalibration (ablation) | DN-Def-DETR R50 · UVO | AP: 26.0 -> 28.4 | Improved |
| replace cascade attention by oracle mask attention using GT masks (ablation) | Cascade-DN-Def-DETR · UVO and COCO | AP: UVO 28.4 vs 29.0; COCO 44.8 vs 44.2 | Mixed |
| use L1/L2 IoU loss instead of Huber loss (ablation) | query recalibration · UVO | AP: 25.3 -> 25.9 | Improved |
| score queries with cls prob times IoU instead of sum fusion (ablation) | query recalibration · UVO | AP: 23.5 -> 25.9 | Improved |
| apply IoU loss only to matched queries instead of all queries (ablation) | query recalibration · UVO | AP: 22.5 -> 25.9 | Improved |
| replace deformable attention in DINO by cascade attention (no QR) (ablation) | DINO · UVO | AP: 30.2 -> 31.9 | Improved |
| use GT boxes early in training to constrain attention (ablation) | Cascade-DINO · UVO | AP: 32.7 -> 29.7 | Hurt |
| constrain deformable attention offsets inside predicted boxes (ablation) | DINO deformable attention · UVO | AP: +0.8 AP, still 1.7 AP below cascade attention | No clear effect |
| Cascade-DN-DETR versus Faster R-CNN on Paintings | Cascade-DN-Def-DETR · Paintings (from ImageNet init) | AP: 17.0 -> 13.4 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 2 of 4 shared results
- Cascade R-CNN — Cascade R-CNN: Delving Into High Quality Object Detection (CVPR 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- End-to-End Object Detection with Transformers (ECCV 2020 · similarity 0.90)
- Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection (ICCV 2023 · similarity 0.90)
- CF-DETR: Coarse-to-Fine Transformers for End-to-End Object Detection (AAAI 2022 · similarity 0.89)
- CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection (AAAI 2025 · similarity 0.89)
- UN-DETR: Promoting Objectness Learning via Joint Supervision for Unknown Object Detection (AAAI 2025 · similarity 0.88)
- MI-DETR: An Object Detection Model with Multi-time Inquiries Mechanism (CVPR 2025 · 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.
