Research map / Label-efficient and robust learning / Recognition and long-tail
Soft Contrastive Learning for Visual Localization
Janine Thoma, Danda Pani Paudel, Luc V. Gool
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 |
|---|---|---|---|
| replace hard positive/negative assignment (triplet) with soft assignment loss | VGG-16 + NetVLAD · Oxford RobotCar + Pittsburgh mean at 5 m | localization accuracy (%): 55.1 -> 60.7 | Improved |
| soft contrastive loss vs multi-similarity loss (previous SOTA) | VGG-16 + NetVLAD · Oxford RobotCar + Pittsburgh mean at 5 m | localization accuracy (%): 57.5 -> 60.7 | Improved |
| soft contrastive loss vs log-ratio loss (soft but proportional for all pairs) | VGG-16 + NetVLAD · CMU Seasons mean at 5 m | localization accuracy (%): 58.8 -> 70.4 | Improved |
| soft contrastive loss vs multi-similarity loss | VGG-16 + NetVLAD · CMU Seasons mean at 5 m | localization accuracy (%): 66.3 -> 70.4 | Improved |
| soft contrastive loss vs multi-similarity loss | VGG-16 + NetVLAD · RobotCar Seasons mean at 5 m | localization accuracy (%): 67.8 -> 68.9 | Improved |
| use sigmoid influence functions with loss (5) versus linear/tanh influence functions and a simple sum loss (ablation) | soft contrastive loss · Oxford RobotCar and Pittsburgh | localization accuracy | Improved |
Closest papers by meaning
- Divide&Classify: Fine-Grained Classification for City-Wide Visual Geo-Localization (ICCV 2023 · similarity 0.87)
- Yes, we CANN: Constrained Approximate Nearest Neighbors for Local Feature-Based Visual Localization (ICCV 2023 · similarity 0.87)
- MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering (NeurIPS 2025 · similarity 0.86)
- Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency (ICLR 2024 · similarity 0.85)
- Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition (AAAI 2025 · similarity 0.85)
- From Coarse to Fine: A Matching and Alignment Framework for Unsupervised Cross-View Geo-Localization (AAAI 2025 · 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.
