Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
A Zero-Shot Framework for Sketch based Image Retrieval
Sasi Kiran Yelamarthi, Shiva Krishna Reddy, Ashish Mishra, Anurag Mittal
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 |
|---|---|---|---|
| evaluate on unseen classes (zero-shot) instead of traditional split | DSH · Sketchy | Precision@200: 0.866 -> 0.153 | Hurt |
| evaluate on unseen classes instead of traditional split | Siamese-2 · Sketchy | Precision@200: 0.690 -> 0.251 | Hurt |
| evaluate on unseen classes instead of traditional split | Coarse-grained triplet · Sketchy | mAP@200: 0.573 -> 0.083 | Hurt |
| use generative CVAE instead of SAE | SAE · Sketchy ZS-SBIR (zero-shot split) | mAP@200: 0.136 -> 0.225 | Improved |
| use generative CVAE instead of Siamese-2 | Siamese-2 · Sketchy ZS-SBIR (zero-shot split) | Precision@200: 0.251 -> 0.333 | Improved |
| use CAAE instead of Siamese-2 | Siamese-2 · Sketchy ZS-SBIR (zero-shot split) | Precision@200: 0.251 -> 0.260 | Improved |
| use CVAE instead of CAAE | CAAE · Sketchy ZS-SBIR (zero-shot split) | mAP@200: 0.156 -> 0.225 | Improved |
| add reconstruction loss of sketch features (ablation) | CVAE · Sketchy ZS-SBIR (zero-shot split) | Precision@200: 3% improvement on the precision | Improved |
| coarse-grained instead of fine-grained negatives for triplet training | Triplet network · Sketchy ZS-SBIR (zero-shot split) | Precision@200: 0.155 -> 0.169 | Improved |
| replace Direct Regression with ESZSL regularization | Direct Regression · Sketchy ZS-SBIR (zero-shot split) | Precision@200: 0.066 -> 0.187 | Improved |
| add reconstructibility regularization (SAE) to linear mapping | Direct Regression · Sketchy ZS-SBIR (zero-shot split) | Precision@200: 0.066 -> 0.238 | Improved |
Closest papers by meaning
- Doodle to Search: Practical Zero-Shot Sketch-Based Image Retrieval (CVPR 2019 · similarity 0.94)
- Zero-Shot Sketch-Based Image Retrieval via Graph Convolution Network (AAAI 2020 · similarity 0.94)
- Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrieval (CVPR 2019 · similarity 0.94)
- Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval (ICCV 2019 · similarity 0.94)
- CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not (CVPR 2023 · similarity 0.93)
- Asymmetric Mutual Alignment for Unsupervised Zero-Shot Sketch-Based Image Retrieval (AAAI 2024 · similarity 0.91)
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.
