Research map / Detection and segmentation / CNN features
ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
Weicheng Kuo, Anelia Angelova, Jitendra Malik, Tsung-Yi Lin
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 shape priors (ablation) | ShapeMask (embed only) · VOC->Non-VOC | mask AP: 26.2 -> 30.2 | Improved |
| add instance embedding (ablation) | ShapeMask (shape only) · VOC->Non-VOC | mask AP: 26.4 -> 30.2 | Improved |
| add shape priors to the plain baseline (ablation) | baseline mask decoder · VOC->Non-VOC | mask AP: 13.7 -> 26.4 | Improved |
| add instance embedding to the plain baseline (ablation) | baseline mask decoder · VOC->Non-VOC | mask AP: 13.7 -> 26.2 | Improved |
| add shape priors (ablation) | ShapeMask (embed only) · Non-VOC->VOC | mask AP: 29.4 -> 33.3 | Improved |
| add instance embedding (ablation) | ShapeMask (shape only) · Non-VOC->VOC | mask AP: 30.6 -> 33.3 | Improved |
| add shape priors to the plain baseline (ablation) | baseline mask decoder · fully supervised COCO val2017 | mask AP: 35.5 -> 36.9 | Improved |
| add instance embedding to the plain baseline (ablation) | baseline mask decoder · fully supervised COCO val2017 | mask AP: 35.5 -> 36.7 | Improved |
| add both shape priors and instance embedding (ablation) | baseline mask decoder · fully supervised COCO val2017 | mask AP: 35.5 -> 37.2 | Improved |
| train with jittered boxes (ablation) | ShapeMask · jittered detections at test time | mask AP: 34.3 -> 35.7 | Improved |
| jitter test-time detections (ablation) | Mask R-CNN · COCO mask AP | mask AP: 36.4 -> 29.0 | Hurt |
| jitter test-time detections (ablation) | ShapeMask · COCO mask AP | mask AP: 37.2 -> 34.3 | Hurt |
Later papers that compared with this method
6 later accepted papers report ShapeMask as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision (CVPR 2021 · better on 2 of 2 shared results)
- Prior to Segment: Foreground Cues for Weakly Annotated Classes in Partially Supervised Instance Segmentation (ICCV 2021 · better on 2 of 2 shared results)
- The Surprising Impact of Mask-Head Architecture on Novel Class Segmentation (ICCV 2021 · better on 1 of 1 shared result)
- SOTR: Segmenting Objects With Transformers (ICCV 2021 · better on 1 of 1 shared result)
- Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation (ECCV 2020 · better on 3 of 3 shared results)
- Learning Saliency Propagation for Semi-Supervised Instance Segmentation (CVPR 2020 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- PANet — PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (ICCV 2019) · better on 0 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
- BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation (CVPR 2020 · similarity 0.90)
- RefineMask: Towards High-Quality Instance Segmentation With Fine-Grained Features (CVPR 2021 · similarity 0.89)
- BoxInst: High-Performance Instance Segmentation With Box Annotations (CVPR 2021 · similarity 0.89)
- MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation (AAAI 2024 · similarity 0.88)
- The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models (ICLR 2024 · similarity 0.88)
- Training-Free Dataset Pruning for Instance Segmentation (ICLR 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.
