Research map / Label-efficient and robust learning / Self-supervised and contrastive
Self-Supervised Product Quantization for Deep Unsupervised Image Retrieval
Young Kyun Jang, Nam Ik Cho
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 |
|---|---|---|---|
| use cross quantized contrastive learning instead of comparing quantized outputs (ablation) | SPQ · CIFAR-10 (32-bit) | mAP: 0.763 -> 0.793 | Improved |
| use cross quantized contrastive learning instead of comparing quantized outputs (ablation) | SPQ · FLICKR25K (32-bit) | mAP: 0.751 -> 0.769 | Improved |
| use soft quantization instead of hard quantization (ablation) | SPQ · CIFAR-10 (32-bit) | mAP: 0.745 -> 0.793 | Improved |
| use soft quantization instead of hard quantization (ablation) | SPQ · NUS-WIDE (32-bit) | mAP: 0.742 -> 0.774 | Improved |
| use product quantization instead of standard vector quantization (ablation) | SPQ · CIFAR-10 (32-bit) | mAP: 0.734 -> 0.793 | Improved |
| use product quantization instead of standard vector quantization (ablation) | SPQ · FLICKR25K (32-bit) | mAP: 0.733 -> 0.769 | Improved |
| initialize with ImageNet pretrained weights (ablation) | SPQ · CIFAR-10 (32-bit) | mAP: 0.793 -> 0.814 | Improved |
| initialize with ImageNet pretrained weights (ablation) | SPQ · NUS-WIDE (32-bit) | mAP: 0.774 -> 0.788 | Improved |
| use ResNet backbone instead of VGG16 (ablation) | SPQ · CIFAR-10 (32-bit) | mAP: 0.761 -> 0.793 | Improved |
| use SPQ instead of semi-unsupervised TBH | TBH · CIFAR-10 (32-bit) | mAP: 0.573 -> 0.793 | Improved |
| use SPQ instead of BGAN | BGAN · FLICKR25K (32-bit) | mAP: 0.686 -> 0.769 | Improved |
| vary tau_q and tau_cqc hyper-parameters (ablation) | SPQ · CIFAR-10 (32-bit) | mAP | No clear effect |
Closest papers by meaning
- End-To-End Supervised Product Quantization for Image Search and Retrieval (CVPR 2019 · similarity 0.91)
- Generalized Product Quantization Network for Semi-Supervised Image Retrieval (CVPR 2020 · similarity 0.90)
- Deep Visual-Semantic Quantization for Efficient Image Retrieval (CVPR 2017 · similarity 0.90)
- Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval (NeurIPS 2023 · similarity 0.90)
- Deep Quantization Network for Efficient Image Retrieval (AAAI 2016 · similarity 0.89)
- HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval (AAAI 2024 · similarity 0.89)
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.
