Research map / Label-efficient and robust learning / Domain adaptation and generalization
IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval
Haixin Wang, Hao Wu, Jinan Sun, Shikun Zhang, Chong Chen, Xian-Sheng Hua, Xiao Luo
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 reconstruction loss L_RE (ablation) | IDEA · Office-Home C2R | MAP: 44.02 -> 45.71 | Improved |
| Add reconstruction loss L_RE (ablation) | IDEA · Digits USPS2MNIST | MAP: 64.80 -> 67.97 | Improved |
| Add consistency learning loss L_CL (ablation) | IDEA · Office-Home C2R | MAP: 42.11 -> 45.71 | Improved |
| Add consistency learning loss L_CL (ablation) | IDEA · Office31 A2W | MAP: 51.17 -> 54.43 | Improved |
| Add hash code variance under intervention L_V (ablation) | IDEA · Digits USPS2MNIST | MAP: 57.34 -> 67.97 | Improved |
| Add hash code variance under intervention L_V (ablation) | IDEA · Office-Home C2R | MAP: 45.10 -> 45.71 | Improved |
| Add mutual information loss L_MI (ablation) | IDEA · Digits USPS2MNIST | MAP: 67.12 -> 67.97 | Improved |
| Add L_V (extra ablation) (ablation) | IDEA · Office-Home Product2Real | MAP: 58.23 -> 59.18 | Improved |
| Add L_MI (extra ablation) (ablation) | IDEA · Office31 Webcam2Dslr | MAP: 83.71 -> 84.97 | Improved |
| Increase beta (loss weight) (ablation) | IDEA · Office-Home and Office31 sensitivity | MAP | Hurt |
| Increase tau (ablation) | IDEA · Office-Home and Office31 sensitivity | MAP | Mixed |
| Replace PEACE with IDEA | hashing methods · Office-Home + Office31 average, 64-bit | MAP: 51.22 -> 57.03 | Improved |
Closest papers by meaning
- Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.92)
- Domain Adaptive Hashing Retrieval via VLM Assisted Pseudo-Labeling and Dual Space Adaptation (NeurIPS 2025 · similarity 0.92)
- Robust Domain Adaptive Hashing via Structural Noise Modeling and Correction (AAAI 2026 · similarity 0.91)
- PromptHash:Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval (CVPR 2025 · similarity 0.87)
- Deep Unsupervised Hashing via External Guidance (ICML 2025 · similarity 0.86)
- Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization (ICML 2025 · similarity 0.86)
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.
