Research map / Detection and segmentation / CNN features
Class Guided Channel Weighting Network for Fine-Grained Semantic Segmentation
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 |
|---|---|---|---|
| Add CGW to DeepLabv3+ (ablation) | DeepLabv3+ · CUB-200-2011 val | mIoU (%): 64.29 -> 66.51 | Helped |
| Add CRA to DeepLabv3+ (ablation) | DeepLabv3+ · CUB-200-2011 val | mIoU (%): 64.29 -> 65.88 | Helped |
| Add DEGF to DeepLabv3+ (ablation) | DeepLabv3+ · Stanford Cars val | mIoU (%): 65.83 -> 67.62 | Helped |
| Add CGW, CRA, and DEGF together (ablation) | DeepLabv3+ · PASCAL VOC 2012 val | mIoU (%): 75.49 -> 78.25 | Helped |
| Use CGCWNet instead of DSRL | fine-grained segmentation models · FGVC Aircraft | mIoU (%): 68.33 -> 68.62 | Helped |
| Use CGCWNet instead of CTS | fine-grained segmentation models · CUB-200-2011 | mIoU (%): 76.42 -> 67.23 | Hurt |
| Use CGCWNet instead of DSRL | fine-grained segmentation models · Orchid Plant | mIoU (%): 72.01 -> 75.97 | Helped |
| Use CGCWNet instead of CTS | fine-grained segmentation models · Stanford Cars | mIoU (%): 74.68 -> 69.59 | Hurt |
| Use CGCWNet instead of DSRL | fine-grained segmentation models · Multi-Object Aircraft | mIoU (%): 61.81 -> 62.93 | Helped |
| Use CGCWNet instead of DSRL | fine-grained segmentation models · AIBD-Birds | mIoU (%): 57.82 -> 58.51 | Helped |
Closest papers by meaning
- Hierarchically Gated Deep Networks for Semantic Segmentation (CVPR 2016 · similarity 0.87)
- Fine-Grained Image Classification via Combining Vision and Language (CVPR 2017 · similarity 0.87)
- Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation (CVPR 2019 · similarity 0.86)
- Attention to Scale: Scale-Aware Semantic Image Segmentation (CVPR 2016 · similarity 0.86)
- MaSS13K: A Matting-level Semantic Segmentation Benchmark (CVPR 2025 · similarity 0.85)
- Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation (AAAI 2024 · similarity 0.85)
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.