Research map / Detection and segmentation / CNN features
AdaptIS: Adaptive Instance Selection Network
Konstantin Sofiiuk, Olga Barinova, Anton Konushin
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 |
|---|---|---|---|
| add Relative CoordConv block (ablation) | AdaptIS ResNet-50 · Cityscapes val | PQ: 53.9 -> 59.0 | Improved |
| use Normalized Focal Loss instead of Focal Loss (ablation) | AdaptIS ResNet-50 · Cityscapes val | PQ: 55.9 -> 59.0 | Improved |
| use Normalized Focal Loss instead of BCE (ablation) | AdaptIS ResNet-50 · Cityscapes val | PQ: 58.7 -> 59.0 | Improved |
| scale backbone from ResNet-50 to ResNet-101 (ablation) | AdaptIS · Cityscapes val | PQ: 59.0 -> 60.6 | Improved |
| scale backbone from ResNet-101 to ResNeXt-101 (ablation) | AdaptIS · Cityscapes val | PQ: 60.6 -> 62.0 | Improved |
| scale backbone from ResNet-101 to ResNeXt-101 (ablation) | AdaptIS · COCO val | PQ: 37.0 -> 42.3 | Improved |
| scale backbone from ResNet-50 to ResNeXt-101 (ablation) | AdaptIS · Mapillary val | PQ: 32.0 -> 35.9 | Improved |
| use AdaptIS instead of Mask R-CNN on overlapping objects (ablation) | segmentation method · Toy overlapping objects | AP@.9: 5.8% -> 97.5% | Improved |
| use AdaptIS instead of Mask R-CNN on overlapping objects (ablation) | segmentation method · Toy overlapping objects | AP@.5: 74.6% -> 99.6% | Improved |
Later papers that compared with this method
6 later accepted papers report AdaptIS as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Split-GCN: Effective Interactive Annotation for Segmentation of Disconnected Instance (TPAMI 2022 · better on 0 of 1 shared result)
- EfficientPS: Efficient Panoptic Segmentation (IJCV 2021 · better on 2 of 2 shared results)
- Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (CVPR 2020 · better on 1 of 1 shared result)
- Pixel Consensus Voting for Panoptic Segmentation (CVPR 2020 · better on 0 of 1 shared result)
- Joint Semantic Instance Segmentation on Graphs with the Semantic Mutex Watershed (ECCV 2020 · better on 0 of 1 shared result)
- LevelSet R-CNN: A Deep Variational Method for Instance Segmentation (ECCV 2020 · 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 0 of 1 on most shared results.
- UPSNet — UPSNet: A Unified Panoptic Segmentation Network (CVPR 2019) · better on 1 of 2 shared results
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
- Unifying Training and Inference for Panoptic Segmentation (CVPR 2020 · similarity 0.89)
- Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach (NeurIPS 2021 · similarity 0.89)
- Pixelwise Instance Segmentation With a Dynamically Instantiated Network (CVPR 2017 · similarity 0.88)
- Real-Time Panoptic Segmentation From Dense Detections (CVPR 2020 · similarity 0.88)
- Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation (AAAI 2021 · similarity 0.88)
- UPSNet: A Unified Panoptic Segmentation Network (CVPR 2019 · 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.
