Research map / Detection and segmentation / Weakly supervised detection and segmentation
Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation
Qi Fan, Lei Ke, Wenjie Pei, Chi-Keung Tang, Yu-Wing Tai
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 Boundary-Parsing Module (BM) (ablation) | Baseline (ResNet-50) · COCO val voc->non-voc | mask AP: 20.7 -> 27.4 | Improved |
| feed boundary feature to the mask head (FF) in BM (ablation) | Baseline + BM · COCO val voc->non-voc | mask AP: 21.6 -> 27.4 | Improved |
| add Non-local Affinity-Parsing Module (AM) (ablation) | Baseline (ResNet-50) · COCO val voc->non-voc | mask AP: 20.7 -> 27.2 | Improved |
| add affinity loss (AL) to AM (ablation) | Baseline + AM · COCO val voc->non-voc | mask AP: 26.9 -> 27.2 | Improved |
| add AM on top of BM (both modules) (ablation) | Baseline + BM · COCO val voc->non-voc | mask AP: 27.4 -> 28.8 | Improved |
| add BM on top of AM (ablation) | Baseline + AM · COCO val voc->non-voc | mask AP: 27.2 -> 28.8 | Improved |
| use CPMask instead of ShapeMask | ShapeMask · COCO val voc->non-voc | mask AP: 30.2 -> 34.0 | Improved |
| use CPMask instead of ShapeMask | ShapeMask · COCO val non-voc->voc | mask AP: 33.3 -> 36.8 | Improved |
| use CPMask instead of ShapeMask with NAS-FPN | ShapeMask (NAS-FPN) · COCO val voc->non-voc | mask AP: 33.2 -> 34.0 | Improved |
| use CPMask instead of Meta R-CNN | Meta R-CNN · COCO few-shot 10-shot | mask AP: 4.4 -> 7.1 | Improved |
| use CPMask instead of Meta R-CNN | Meta R-CNN · COCO few-shot 20-shot | mask AP: 6.4 -> 10.3 | Improved |
| use FCOS-based CPMask instead of CenterMask | CenterMask · COCO test-dev fully supervised | mask AP: 38.3 -> 39.2 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 on most shared results.
- ShapeMask — ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors (ICCV 2019) · better on 3 of 3 shared results
- CenterMask — CenterMask: Real-Time Anchor-Free Instance Segmentation (CVPR 2020) · better on 1 of 1 shared result
- TensorMask — TensorMask: A Foundation for Dense Object Segmentation (ICCV 2019) · better on 1 of 1 shared result
- PANet — PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (ICCV 2019) · better on 0 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
- Learning to Segment Every Thing (CVPR 2018 · similarity 0.90)
- Prior to Segment: Foreground Cues for Weakly Annotated Classes in Partially Supervised Instance Segmentation (ICCV 2021 · similarity 0.90)
- ContrastMask: Contrastive Learning To Segment Every Thing (CVPR 2022 · similarity 0.90)
- ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors (ICCV 2019 · similarity 0.89)
- Training-Free Dataset Pruning for Instance Segmentation (ICLR 2025 · similarity 0.88)
- The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models (ICLR 2024 · similarity 0.87)
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.
