Research map / Detection and segmentation / CNN features
HoughNet: Integrating near and long-range evidence for bottom-up object detection
Nermin Samet, Samet Hicsonmez, Emre Akbas
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 voting module to OAP baseline (ablation) | OAP R-101-DCN · COCO val | AP: 36.2 -> 37.3 | Improved |
| replace voting module with dilated convolution (ablation) | OAP R-101-DCN · COCO val | AP: 37.3 -> 36.6 | Hurt |
| add dilated convolution to baseline (ablation) | OAP R-101-DCN · COCO val | AP: 36.2 -> 36.6 | Improved |
| add voting module to OAP baseline for small objects (ablation) | OAP R-101-DCN · COCO val | AP_S: 16.3 -> 16.8 | Improved |
| keep only the center ring of the vote field (remove outer rings) (ablation) | HoughNet · COCO val (ablation setting) | AP: 23.8 -> 24.6 | Improved |
| add the center ring when using only outer rings (ablation) | HoughNet · COCO val (ablation setting) | AP: 24.4 -> 24.6 | Improved |
| add inner rings to context-only voting (ablation) | HoughNet · COCO val (ablation setting) | AP: 23.6 -> 24.6 | Improved |
| vary number of angle bins 60 to 360 degrees (ablation) | HoughNet · COCO val (ablation setting) | AP: 24.6 -> 24.5 | No clear effect |
| reduce rings from 5 to 3 (ablation) | HoughNet · COCO val (ablation setting) | AP: 24.6 -> 24.8 | Improved |
| reduce rings from 5 to 3 (ablation) | HoughNet · COCO val (ablation setting) | FPS: 3.5 -> 15.6 | Improved |
| add ExtremeNet weight initialization | HoughNet HG-104 (SS) · COCO test-dev | AP: 40.8 -> 43.1 | Improved |
| add voting module to CycleGAN | CycleGAN · Cityscapes | Per-pixel acc.: 0.43 -> 0.52 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 2 on most shared results.
- PANet — PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (ICCV 2019) · better on 0 of 1 shared result
- FCOS — FCOS: Fully Convolutional One-Stage Object Detection (ICCV 2019) · better on 0 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
- HoughNet: Integrating Near and Long-Range Evidence for Visual Detection (TPAMI 2022 · similarity 0.98)
- ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models (NeurIPS 2019 · similarity 0.89)
- Deep Hough Voting for 3D Object Detection in Point Clouds (ICCV 2019 · similarity 0.88)
- DeNet: Scalable Real-Time Object Detection With Directed Sparse Sampling (ICCV 2017 · similarity 0.88)
- Latent-Class Hough Forests for 6 DoF Object Pose Estimation (TPAMI 2017 · similarity 0.87)
- Learning Rich Features at High-Speed for Single-Shot Object Detection (ICCV 2019 · 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.
