Research map / Vision-language and multimodal / CLIP and zero-shot
Zero-Shot Sketch-Image Hashing
Read the paperCheck 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 |
|---|---|---|---|
| Use ZSIH instead of the strongest listed SBIR baseline, GN Triplet | Zero-shot SBIR · Sketchy (Extended) | mAP@all: 0.211 -> 0.254 | Helped |
| Use ZSIH instead of the strongest listed SBIR baseline, GN Triplet | Zero-shot SBIR · TU-Berlin (Extended) | mAP@all: 0.189 -> 0.220 | Helped |
| Use Kronecker fusion instead of feature concatenation (ablation) | ZSIH · Sketchy and TU-Berlin (Extended), 64-bit | mAP@all: 0.228 -> 0.254; 0.207 -> 0.220 | Helped |
| Use Kronecker fusion instead of MFB (ablation) | ZSIH · Sketchy and TU-Berlin (Extended), 64-bit | mAP@all: 0.236 -> 0.254; 0.211 -> 0.220 | Helped |
| Use stochastic neurons instead of bit regularization (ablation) | ZSIH · Sketchy and TU-Berlin (Extended), 64-bit | mAP@all: 0.187 -> 0.254; 0.158 -> 0.220 | Helped |
| Use a semantic decoder instead of a classifier (ablation) | ZSIH · Sketchy and TU-Berlin (Extended), 64-bit | mAP@all: 0.162 -> 0.254; 0.133 -> 0.220 | Helped |
| Add graph convolutional layers (ablation) | ZSIH · Sketchy and TU-Berlin (Extended), 64-bit | mAP@all: 0.233 -> 0.254; 0.171 -> 0.220 | Helped |
| Use graph convolution instead of word-vector fusion (ablation) | ZSIH · Sketchy and TU-Berlin (Extended), 64-bit | mAP@all: 0.219 -> 0.254; 0.176 -> 0.220 | Helped |
| Set GCN adjacency temperature t to 1 instead of the full-model setting (ablation) | ZSIH · Sketchy and TU-Berlin (Extended), 64-bit | mAP@all: 0.062 -> 0.254; 0.055 -> 0.220 | Hurt |
| Set GCN adjacency temperature t to 10^-6 instead of the full-model setting (ablation) | ZSIH · Sketchy and TU-Berlin (Extended), 64-bit | mAP@all: 0.241 -> 0.254; 0.202 -> 0.220 | Hurt |
Closest papers by meaning
- Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval (CVPR 2017 · similarity 0.92)
- Zero-Shot Sketch-Based Image Retrieval via Graph Convolution Network (AAAI 2020 · similarity 0.92)
- Doodle to Search: Practical Zero-Shot Sketch-Based Image Retrieval (CVPR 2019 · similarity 0.92)
- Asymmetric Mutual Alignment for Unsupervised Zero-Shot Sketch-Based Image Retrieval (AAAI 2024 · similarity 0.91)
- ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling (AAAI 2025 · similarity 0.88)
- Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers (CVPR 2024 · 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.