Research map / Label-efficient and robust learning / Recognition and long-tail
Exploiting Multi-Grain Ranking Constraints for Precisely Searching Visually-Similar Vehicles
Ke Yan, Yonghong Tian, Yaowei Wang, Wei Zeng, Tiejun Huang
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 vehicle model and color classification to ID classification (ablation) | VGG_CNN_M_1024 · VehicleID (small) | mAP: 0.597 -> 0.625 | Improved |
| add vehicle model and color classification to ID classification (ablation) | VGG_CNN_M_1024 · VehicleID (large) | mAP: 0.552 -> 0.575 | Improved |
| use ID classification instead of CCL ranking | VGG_CNN_M_1024 · VehicleID (large) | mAP: 0.455 -> 0.552 | Improved |
| use GoogLeNet instead of VGG for multi-attribute classification (ablation) | ATTs · VehicleID (large) | mAP: 0.575 -> 0.586 | Improved |
| use GoogLeNet instead of VGG for multi-attribute classification (ablation) | ATTs · VehicleID (small) | mAP: 0.625 -> 0.628 | No clear effect |
| train from scratch instead of fine-tuning from ImageNet (ablation) | ATTs GoogLeNet · VD1 (large) | mAP: 0.239 -> 0.461 | Improved |
| train from scratch instead of fine-tuning from ImageNet (ablation) | ATTs GoogLeNet · VD2 (large) | mAP: 0.317 -> 0.492 | Improved |
| add pairwise ranking to attribute classification (ablation) | ATTs · VD1 (large) | mAP: 0.461 -> 0.474 | Improved |
| add triplet ranking to attribute classification (ablation) | ATTs · VD1 (large) | mAP: 0.461 -> 0.482 | Improved |
| add generalized pairwise ranking (multi-grain) to attribute classification (ablation) | ATTs · VD1 (large) | mAP: 0.461 -> 0.501 | Improved |
| add multi-grain list ranking to attribute classification (ablation) | ATTs · VD1 (large) | mAP: 0.461 -> 0.511 | Improved |
| add generalized pairwise ranking (multi-grain) to attribute classification (ablation) | ATTs · VD2 (large) | mAP: 0.492 -> 0.537 | Improved |
Closest papers by meaning
- SearchAD: Large-Scale Rare Image Retrieval Dataset for Autonomous Driving (CVPR 2026 · similarity 0.87)
- Deep Relative Distance Learning: Tell the Difference Between Similar Vehicles (CVPR 2016 · similarity 0.86)
- Learning Coarse-to-Fine Structured Feature Embedding for Vehicle Re-Identification (AAAI 2018 · similarity 0.83)
- Embedding Label Structures for Fine-Grained Feature Representation (CVPR 2016 · similarity 0.83)
- Structural Information Guided Multimodal Pre-training for Vehicle-Centric Perception (AAAI 2024 · similarity 0.82)
- Infer the Whole from a Glimpse of a Part: Keypoint-Based Knowledge Graph for Vehicle Re-Identification (AAAI 2025 · 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.
