Diverse Sampling for Self-Supervised Learning of Semantic Segmentation
원문 초록
We propose an approach for learning category-level semantic segmentation purely from image-level classification tags indicating presence of categories. It exploits localization cues that emerge from training classification-tasked convolutional networks, to drive a "self-supervision" process that automatically labels a sparse, diverse training set of points likely to belong to classes of interest. Our approach has almost no hyperparameters, is modular, and allows for very fast training of segmentation in less than 3 minutes. It obtains competitive results on the VOC 2012 segmentation benchmark. More, significantly the modularity and fast training of our framework allows new classes to efficiently added for inference.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MACD R-CNN: An Abnormal Cell Nucleus Detection Method
SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction
A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique
Unified Medical Image Segmentation with State Space Modeling Snake
SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation
DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.