Research map / Detection and segmentation / CNN features
ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation
Zhenchao Jin, Bin Liu, Qi Chu, Nenghai Yu
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 the image-level context module (ILCM) (ablation) | ResNet-50 baseline · ADE20K val (single-scale) | mIoU: 36.96 -> 42.50 | Improved |
| add the semantic-level context module (SLCM) (ablation) | ResNet-50 baseline · ADE20K val (single-scale) | mIoU: 36.96 -> 42.89 | Improved |
| add SLCM on top of ILCM (ablation) | ISNet ResNet-50 · ADE20K val (single-scale) | mIoU: 42.50 -> 44.09 | Improved |
| add ILCM on top of SLCM (ablation) | ISNet ResNet-50 · ADE20K val (single-scale) | mIoU: 42.89 -> 44.09 | Improved |
| replace ILCM with ASPP as image-level module | ISNet ResNet-101 · LIP val | mIoU: 55.41 -> 56.96 | Improved |
| add SLCM to ASPP | ASPP ResNet-101 · LIP val | mIoU: 55.34 -> 56.96 | Improved |
| replace ILCM with ASPP as image-level module | ISNet ResNet-101 · Cityscapes val (single-scale) | mIoU: 80.56 -> 81.10 | Improved |
| use ResNet-101 instead of ResNet-50 | ISNet · ADE20K val (multi-scale + flip) | mIoU: 45.04 -> 47.31 | Improved |
| use ResNeSt-101 instead of ResNet-101 | ISNet · ADE20K val (multi-scale + flip) | mIoU: 47.31 -> 47.55 | Improved |
| use ResNeSt-101 instead of ResNet-101 | ISNet · COCOStuff test (multi-scale + flip) | mIoU: 41.60 -> 42.08 | Improved |
| use ResNeSt-101 instead of ResNet-101 | ISNet · LIP val | mIoU: 55.41 -> 56.81 | Improved |
| use ISNet context module instead of DNL | ResNet-50 context scheme · ADE20K val (single-scale) | mIoU: 43.50 -> 44.09 | Improved |
Later papers that compared with this method
7 later accepted papers report IS-Net as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.
- High-Quality Entity Segmentation and Grounding (TPAMI 2026 · better on 2 of 2 shared results)
- Learning from Adversity: Semantic-Aware Mask Refinement through Adversarial Perturbation (ECCV 2026 · better on 1 of 1 shared result)
- IRMamba: Pixel Difference Mamba with Layer Restoration for Infrared Small Target Detection (AAAI 2025 · better on 2 of 2 shared results)
- TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection (AAAI 2024 · better on 5 of 5 shared results)
- IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection (ECCV 2024 · better on 4 of 4 shared results)
- Infrared Small Target Detection with Scale and Location Sensitivity (CVPR 2024 · better on 1 of 1 shared result)
- MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation (TPAMI 2022 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CCNet — CCNet: Criss-Cross Attention for Semantic Segmentation (ICCV 2019) · better on 1 of 1 shared result
- DANet — DANet: Divergent Activation for Weakly Supervised Object Localization (ICCV 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Multi-Scale Context Intertwining for Semantic Segmentation (ECCV 2018 · similarity 0.91)
- Mining Contextual Information Beyond Image for Semantic Segmentation (ICCV 2021 · similarity 0.91)
- Object-Contextual Representations for Semantic Segmentation (ECCV 2020 · similarity 0.90)
- Cross-Image Pixel Contrasting for Semantic Segmentation (TPAMI 2024 · similarity 0.89)
- Hierarchy-Agnostic Unsupervised Segmentation: Parsing Semantic Image Structure (NeurIPS 2024 · similarity 0.88)
- Integrating Low-Level Visual Cues for Enhanced Unsupervised Semantic Segmentation (AAAI 2025 · similarity 0.88)
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.
