Research map / Detection and segmentation / CNN features
Feature Pyramid Transformer
Dong Zhang, Hanwang Zhang, Jinhui Tang, Meng Wang, Xiansheng Hua, Qianru Sun
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 self-transformer (ST) (ablation) | BFP · COCO 2017 val (detection/instance seg) | box AP: 31.6 -> 32.0 | Improved |
| add grounding transformer (GT) (ablation) | BFP · COCO 2017 val (detection/instance seg) | box AP: 31.6 -> 35.1 | Improved |
| add rendering transformer (RT) (ablation) | BFP · COCO 2017 val (detection/instance seg) | box AP: 31.6 -> 34.7 | Improved |
| add all three transformers (full FPT) (ablation) | BFP · COCO 2017 val (detection/instance seg) | box AP: 31.6 -> 38.0 | Improved |
| add SBN to FPT (ablation) | FPT · COCO 2017 val (detection/instance seg) | box AP: 37.2 -> 37.8 | Improved |
| add DropBlock to FPT (ablation) | FPT · COCO 2017 val (detection/instance seg) | box AP: 37.2 -> 37.5 | Improved |
| add SBN and DropBlock together to FPT (ablation) | FPT · COCO 2017 val (detection/instance seg) | box AP: 37.2 -> 38.0 | Improved |
| use Euclidean similarity instead of softmax dot-product in GT (ablation) | BFP+GT · COCO 2017 val (detection/instance seg) | box AP: 32.2 -> 33.7 | Improved |
| add mixture of softmaxes (MoS) to Euclidean GT (ablation) | BFP+GT · COCO 2017 val (detection/instance seg) | box AP: 33.7 -> 34.7 | Improved |
| increase MoS components N in ST from 2 to 8 (ablation) | BFP+ST · COCO 2017 val (detection/instance seg) | box AP: 31.8 -> 30.0 | Hurt |
| increase MoS components N in GT from 4 to 8 (ablation) | BFP+GT · COCO 2017 val (detection/instance seg) | box AP: 34.7 -> 32.5 | Hurt |
| enlarge LGT square_size from 5 to 9 (ablation) | UFP+LGT · Cityscapes val | mIoU: 80.0 -> 79.6 | Hurt |
Closest papers by meaning
- Feature Pyramid Networks for Object Detection (CVPR 2017 · similarity 0.91)
- Transformer-Based Context Condensation for Boosting Feature Pyramids in Object Detection (IJCV 2023 · similarity 0.90)
- Scale-Equalizing Pyramid Convolution for Object Detection (CVPR 2020 · similarity 0.89)
- Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction Without Convolutions (ICCV 2021 · similarity 0.88)
- Inverted Pyramid Multi-task Transformer for Dense Scene Understanding (ECCV 2022 · similarity 0.88)
- ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions (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.
