Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles
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 triplet loss with coupled clusters loss (ablation) | VGG vehicle embedding · VehicleID retrieval (Small, Medium, Large) | MAP: 0.444 -> 0.492; 0.391 -> 0.448; 0.373 -> 0.386 | Helped |
| add the mixed-difference network to the VGG+CCL model (ablation) | VGG vehicle embedding · VehicleID retrieval (Small, Medium, Large) | MAP: 0.492 -> 0.546; 0.448 -> 0.481; 0.386 -> 0.455 | Helped |
| replace triplet loss with coupled clusters loss (ablation) | VGG vehicle embedding · VehicleID re-identification (Small, Medium, Large) | top-1 match rate: 0.404 -> 0.436; 0.354 -> 0.370; 0.319 -> 0.329 | Helped |
| add the mixed-difference network to the VGG+CCL model (ablation) | VGG vehicle embedding · VehicleID re-identification (Small, Medium, Large) | top-1 match rate: 0.436 -> 0.490; 0.370 -> 0.428; 0.329 -> 0.382 | Helped |
| replace triplet loss with coupled clusters loss (ablation) | VGG vehicle embedding · VehicleID re-identification (Small, Medium, Large) | top-5 match rate: 0.617 -> 0.642; 0.546 -> 0.571; 0.503 -> 0.533 | Helped |
| add the mixed-difference network to the VGG+CCL model (ablation) | VGG vehicle embedding · VehicleID re-identification (Small, Medium, Large) | top-5 match rate: 0.642 -> 0.735; 0.571 -> 0.668; 0.533 -> 0.616 | Helped |
| use Mixed Diff+CCL instead of GoogleNet+Joint Bayesian | vehicle model verification · CompCars (Easy, Medium, Hard) | accuracy: 0.833 -> 0.833; 0.824 -> 0.788; 0.761 -> 0.703 | Mixed |
Closest papers by meaning
- Learning Coarse-to-Fine Structured Feature Embedding for Vehicle Re-Identification (AAAI 2018 · similarity 0.88)
- Part-Regularized Near-Duplicate Vehicle Re-Identification (CVPR 2019 · similarity 0.88)
- PhD Learning: Learning With Pompeiu-Hausdorff Distances for Video-Based Vehicle Re-Identification (CVPR 2021 · similarity 0.86)
- Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification (AAAI 2025 · similarity 0.84)
- CLIP-driven View-aware Prompt Learning for Unsupervised Vehicle Re-identification (AAAI 2025 · similarity 0.83)
- Structural Information Guided Multimodal Pre-training for Vehicle-Centric Perception (AAAI 2024 · similarity 0.82)
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.