Research map / Detection and segmentation / Open-set and few-shot detection
A Framework to Coordinate Segmentation and Recognition
Wei Huang, Huimin Yu, Weiwei Zheng, Jing Zhang
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 |
|---|---|---|---|
| Replace capsule encoder with standard CNN encoder (ablation) | coordination framework · Signs and logos | mean IoU (%): 91.00 -> 86.52 | Hurt |
| Replace capsule encoder with standard CNN encoder (ablation) | coordination framework · Signs and logos | accuracy (%): 98.01 -> 90.17 | Hurt |
| Replace capsule encoder with standard CNN encoder (ablation) | coordination framework · Hand gestures | mean IoU (%): 90.57 -> 88.38 | Hurt |
| Replace capsule encoder with standard CNN encoder (ablation) | coordination framework · Hand gestures | accuracy (%): 97.75 -> 91.00 | Hurt |
| Joint iterative segmentation and recognition vs RBM shape-prior segmentation (MMBM) | proposed framework · Signs and logos | mean IoU (%): 84.43 -> 91.00 | Improved |
| Proposed framework vs DeepLab | proposed framework · Signs and logos | mean IoU (%): 79.29 -> 91.00 | Improved |
| Proposed framework vs MMBM | proposed framework · Hand gestures | mean IoU (%): 87.26 -> 90.57 | Improved |
| Proposed framework vs original dataset classifier | proposed framework · Hand gestures | accuracy (%): 89.90 -> 97.75 | Improved |
Closest papers by meaning
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.84)
- Unsupervised Part Representation by Flow Capsules (ICML 2021 · similarity 0.84)
- BAE-NET: Branched Autoencoder for Shape Co-Segmentation (ICCV 2019 · similarity 0.84)
- ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors (ICCV 2019 · similarity 0.84)
- Segmentation-Aware Convolutional Networks Using Local Attention Masks (ICCV 2017 · similarity 0.84)
- BLADE: Box-Level Supervised Amodal Segmentation through Directed Expansion (AAAI 2024 · similarity 0.82)
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.
