Research map / Detection and segmentation / CNN features
SOLO: Segmenting Objects by Locations
Xinlong Wang, Tao Kong, Chunhua Shen, Yuning Jiang, Lei Li
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 FPN multi-level prediction (five pyramids) over best single-scale grid (ablation) | SOLO · COCO val2017 | mask AP: 29.0 -> 35.8 | Improved |
| increase grid number from 12 to 24 (single-scale) (ablation) | SOLO · COCO val2017 | mask AP: 27.2 -> 29.0 | Improved |
| increase grid number from 24 to 36 (single-scale) (ablation) | SOLO · COCO val2017 | mask AP: 29.0 -> 28.6 | Hurt |
| add one CoordConv layer (ablation) | SOLO · COCO val2017 | mask AP: 32.2 -> 35.8 | Improved |
| add second and third CoordConv layers (ablation) | SOLO · COCO val2017 | mask AP: 35.8 -> 35.7 / 35.8 | No clear effect |
| use Focal Loss instead of BCE for mask loss (ablation) | SOLO · COCO val2017 | mask AP: 30.0 -> 31.6 | Improved |
| use Dice Loss instead of Focal Loss for mask loss (ablation) | SOLO · COCO val2017 | mask AP: 31.6 -> 35.8 | Improved |
| use Dice loss instead of BCE for mask loss (ablation) | Mask R-CNN · COCO val2017 | mask AP: 36.2 -> 35.3 | Hurt |
| increase mask head depth from 4 to 7 (ablation) | SOLO · COCO val2017 | mask AP: 34.6 -> 35.8 | Improved |
| increase mask head depth from 7 to 8 (ablation) | SOLO · COCO val2017 | mask AP: 35.8 -> 35.8 | No clear effect |
| change category-branch alignment (interpolation, adaptive-pool, region-grid-interpolation) (ablation) | SOLO · COCO val2017 | mask AP: +/- 0.1 AP | No clear effect |
| decouple the S^2 mask channels into X and Y tensors (ablation) | SOLO · COCO test-dev / val2017 | mask AP: 0.6 AP gains | Improved |
Later papers that compared with this method
7 later accepted papers report SOLO as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation (CVPR 2021 · better on 1 of 1 shared result)
- SOTR: Segmenting Objects With Transformers (ICCV 2021 · better on 1 of 1 shared result)
- Real-Time Instance Segmentation With Discriminative Orientation Maps (ICCV 2021 · better on 0 of 1 shared result)
- BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation (CVPR 2020 · better on 1 of 1 shared result)
- Deep Variational Instance Segmentation (NeurIPS 2020 · better on 0 of 1 shared result)
- SOLOv2: Dynamic and Fast Instance Segmentation (NeurIPS 2020 · better on 1 of 1 shared result)
- Dense RepPoints: Representing Visual Objects with Dense Point Sets (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 3 of 3 on most shared results.
- TensorMask — TensorMask: A Foundation for Dense Object Segmentation (ICCV 2019) · better on 2 of 2 shared results
- PolarMask — PolarMask: Single Shot Instance Segmentation With Polar Representation (CVPR 2020) · better on 1 of 1 shared result
- MaskLab+ — MaskLab: Instance Segmentation by Refining Object Detection With Semantic and Direction Features (CVPR 2018) · 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
- SOLO: A Simple Framework for Instance Segmentation (TPAMI 2021 · similarity 0.97)
- SOLOv2: Dynamic and Fast Instance Segmentation (NeurIPS 2020 · similarity 0.92)
- Pixelwise Instance Segmentation With a Dynamically Instantiated Network (CVPR 2017 · similarity 0.92)
- Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity (CVPR 2022 · similarity 0.91)
- BoxInst: High-Performance Instance Segmentation With Box Annotations (CVPR 2021 · similarity 0.91)
- Training-Free Dataset Pruning for Instance Segmentation (ICLR 2025 · similarity 0.90)
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.
