Learning a Weight Map for Weakly-Supervised Localization
원문 초록
In the weakly supervised localization setting, supervision is given as an image-level label. We propose to employ an image classifier $f$ and to train a generative network $g$ that outputs, given the input image, a per-pixel weight map that indicates the location of the object within the image. Network $g$ is trained by minimizing the discrepancy between the output of the classifier $f$ on the original image and its output given the same image weighted by the output of $g$. The scheme requires a regularization term that ensures that $g$ does not provide a uniform weight, and an early stopping criterion in order to prevent $g$ from over-segmenting the image. Our results indicate that the method outperforms existing localization methods by a sizable margin on the challenging fine-grained classification datasets, as well as a generic image recognition dataset. Additionally, the obtained weight map is also state-of-the-art in weakly supervised segmentation in fine-grained categorization datasets.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Weakly Supervised Segmentation Framework for Thyroid Nodule Based on High-confidence Labels and High-rationality Losses
HELPNet: Hierarchical Perturbations Consistency and Entropy-guided Ensemble for Scribble Supervised Medical Image Segmentation
Upsampling DINOv2 features for unsupervised vision tasks and weakly supervised materials segmentation
Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
Model Guidance via Explanations Turns Image Classifiers into Segmentation Models
Competing for pixels: a self-play algorithm for weakly-supervised segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.