Research map / Architectures and efficiency / CNN design
Convolutional Hough Matching Networks
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 |
|---|---|---|---|
| replace CHM with global RHM voting (ablation) | CHMNet · SPair-71k | PCK (α_bbox=0.1): 46.3 -> 38.2 | Hurt |
| remove all CHM layers (ablation) | CHMNet · SPair-71k | PCK (α_bbox=0.1): 46.3 -> 21.6 | Hurt |
| remove the last 4D CHM layer (ablation) | CHMNet · SPair-71k | PCK (α_bbox=0.1): 46.3 -> 43.1 | Hurt |
| remove Gaussian kernel G from flow formation (ablation) | CHMNet · SPair-71k | PCK (α_bbox=0.1): 46.3 -> 45.5 | Hurt |
| remove the soft keypoint sampler (ablation) | CHMNet · SPair-71k | PCK (α_bbox=0.1): 46.3 -> 43.8 | Hurt |
| replace position-sensitive isotropic kernels with unshared full kernels (ablation) | CHMNet · SPair-71k | PCK (α_bbox=0.1): 46.4 -> 44.8 | Hurt |
| replace position-sensitive isotropic kernels with fully isotropic kernels (ablation) | CHMNet · SPair-71k | PCK (α_bbox=0.1): 46.4 -> 44.9 | Hurt |
| extend the position-sensitive voting space from 4D to 6D to include scale (ablation) | CHMNet · SPair-71k | PCK (α_bbox=0.1): 44.5 -> 46.4 | Helped |
| use sparse correlations with K nearest neighbors (ablation) | CHMNet · SPair-71k | PCK (α_bbox=0.1): 46.4 -> 45.2 | No clear effect |
| increase the number of CHM kernels (channel size) (ablation) | CHMNet · PF-PASCAL and SPair-71k | PCK | Mixed |
Closest papers by meaning
- Convolutional Neural Network Architecture for Geometric Matching (CVPR 2017 · similarity 0.91)
- Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence (ICLR 2024 · similarity 0.86)
- Pixel-level Semantic Correspondence through Layout-aware Representation Learning and Multi-scale Matching Integration (CVPR 2024 · similarity 0.86)
- MATCHA: Towards Matching Anything (CVPR 2025 · similarity 0.86)
- Hierarchical Object-Aware Dual-Level Contrastive Learning for Domain Generalized Stereo Matching (NeurIPS 2024 · similarity 0.86)
- OmniGlue: Generalizable Feature Matching with Foundation Model Guidance (CVPR 2024 · similarity 0.85)
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.