Research map / Detection and segmentation / Weakly supervised detection and segmentation
Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use the multi-evidence weakly supervised pipeline | semantic segmentation · PASCAL VOC 2012 segmentation test | mIoU: 55.6 vs 53.8 | Helped |
| use the multi-evidence weakly supervised pipeline | object detection · PASCAL VOC 2007 detection test | mAP: 51.2 vs 47.0 | Helped |
| add a segmentation branch for multi-task learning | ResNet-101 multi-label classification · MS-COCO 2014 validation | F1-C: 72.8 -> 74.9 | Helped |
| add a segmentation branch for multi-task learning | ResNet-101 multi-label classification · MS-COCO 2014 validation | F1-O: 76.3 -> 78.4 | Helped |
| add object instances and their instance attention maps (ablation) | the proposed object detection pipeline · PASCAL VOC 2007 detection test | mAP: 48.1 -> 51.2; decreased by 3.1% | Helped |
| add clustering and outlier detection (ablation) | the proposed object detection pipeline · PASCAL VOC 2007 detection test | mAP: 48.5 -> 51.2; decreased by 2.7% | Helped |
| retain uncertainty rather than label every pixel (ablation) | the proposed object detection pipeline · PASCAL VOC 2007 detection test | mAP: 47.5; 3.7% lower than the original pipeline | Helped |
Closest papers by meaning
- Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation (CVPR 2019 · similarity 0.91)
- Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation (CVPR 2017 · similarity 0.91)
- Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features (CVPR 2018 · similarity 0.90)
- Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning (ICLR 2021 · similarity 0.90)
- Less Is More: Label Recommendation for Weakly Supervised Point Cloud Semantic Segmentation (AAAI 2024 · similarity 0.88)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · 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.