https://github.com/MindSpore-scientific/code-2/tree/main/weakly-supervised
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
The semantic segmentation task is to assign a label from a label set to each pixel in an image. In the case of fully supervised setting, the dataset consists of images and their corresponding pixel-level class-specific annotations (expensive pixel-level annotations). However, in the weakly-supervised setting, the dataset consists of images and corresponding annotations that are relatively easy to obtain, such as tags/labels of objects present in the image.
<span style="color:grey; opacity: 0.6">( Image credit: Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds
Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
Puzzle-CAM: Improved localization via matching partial and full features
Learning Whole-Slide Segmentation from Inexact and Incomplete Labels using Tissue Graphs
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
Cross Language Image Matching for Weakly Supervised Semantic Segmentation
Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
Puzzle-CAM: Improved localization via matching partial and full features
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
Pseudo-mask Matters in Weakly-supervised Semantic Segmentation
Learning Whole-Slide Segmentation from Inexact and Incomplete Labels using Tissue Graphs
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
Towards Single Stage Weakly Supervised Semantic Segmentation
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling
Adaptive Early-Learning Correction for Segmentation from Noisy Annotations
Puzzle-CAM: Improved localization via matching partial and full features
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.