Research map / Image generation / Editing and style transfer
Image Cropping With Spatial-Aware Feature and Rank Consistency
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 spatial-aware features and rank consistency (ablation) | Image cropping model with MobileNetv2 · GAICD | Acc5: 61.7 -> 64.8 | Helped |
| Use spatial-aware features and rank consistency (ablation) | Image cropping model with MobileNetv2 · GAICD | SRCC: 0.858 -> 0.872 | Helped |
| Add spatial-aware features (ablation) | Image cropping model with MobileNetv2 · GAICD | Acc5: 61.7 -> 63.7 | Helped |
| Add rank consistency on unlabeled images (ablation) | Image cropping model with MobileNetv2 · GAICD | Acc5: 61.7 -> 64.0 | Helped |
| Concatenate feature-map layers instead of averaging them (ablation) | Spatial-aware feature · GAICD | SRCC: 0.862 -> 0.865 | Helped |
| Add channel attention (ablation) | Spatial-aware feature · GAICD | SRCC: 0.863 -> 0.865 | Helped |
| Append the crop mask to the aggregated feature map (ablation) | Spatial-aware feature · GAICD | SRCC: 0.860 -> 0.865 | Helped |
| Use our full method rather than TransView | Image cropping · GAICD | SRCC: 0.857 -> 0.872 | Helped |
| Use our full method rather than TransView | Image cropping · GAICD | Acc5: 63.9 -> 64.8 | Helped |
| Use our full method rather than ASM | Image cropping · FCDB | IoU: 0.749 -> 0.695 | Hurt |
Closest papers by meaning
- Spatial-Semantic Collaborative Cropping for User Generated Content (AAAI 2024 · similarity 0.89)
- Cropper: Vision-Language Model for Image Cropping through In-Context Learning (CVPR 2025 · similarity 0.87)
- Learning Subject-Aware Cropping by Outpainting Professional Photos (AAAI 2024 · similarity 0.86)
- Training-free Detection of AI-generated images via Cropping Robustness (NeurIPS 2025 · similarity 0.83)
- Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping (CVPR 2026 · similarity 0.83)
- Exact: Exploring Space-Time Perceptive Clues for Weakly Supervised Satellite Image Time Series Semantic Segmentation (CVPR 2025 · similarity 0.83)
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.