Universal Correspondence Network
Christopher B. Choy, Manmohan Chandraker, JunYoung Gwak, Silvio Savarese
–Neural Information Processing Systems
We propose a convolutional spatial transformer to mimic patch normalization in traditional features like SIFT, which is shown to dramatically boost accuracy for semantic correspondences across intra-class shape variations.
Neural Information Processing Systems
Nov-21-2025, 09:12:31 GMT
- Country:
- Asia > Japan
- Honshū > Chūbu > Ishikawa Prefecture > Kanazawa (0.04)
- Europe > Spain
- Catalonia > Barcelona Province > Barcelona (0.04)
- North America > United States
- California > Santa Clara County > Palo Alto (0.05)
- Asia > Japan
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (0.95)
- Representation & Reasoning (1.00)
- Vision (1.00)
- Information Technology > Artificial Intelligence