Exploiting saliency for object segmentation from image level labels
There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic labeller network from image-level annotations of the present object classes. Recently, it has been shown that high quality seeds indicating discriminative object regions can be obtained from image-level labels. Without additional information, obtaining the full extent of the object is an inherently ill-posed problem due to co-occurrences. We propose using a saliency model as additional information and hereby exploit prior knowledge on the object extent and image statistics. We show how to combine both information sources in order to recover 80% of the fully supervised performance - which is the new state of the art in weakly supervised training for pixel-wise semantic labelling. The code is available at https://goo.gl/KygSeb.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectSemantic SegmentationSimilar Papers 제목 키워드 기반
Saliency guided deep network for weakly-supervised image segmentation
Weakly-supervised image segmentation is an important task in computer vision. A key problem is how to obtain high quality objects location from image-level category. Classification activation mapping is a common method w…
Image SegmentationSegmentationSemantic SegmentationSaliency maps on image hierarchies
In this paper we propose two saliency models for salient object segmentation based on a hierarchical image segmentation, a tree-like structure that represents regions at different scales from the details to the whole ima…
Image SegmentationSegmentationSemantic SegmentationSalient object detection on hyperspectral images using features learned from unsupervised segmentation task
Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes. However, developments on hyperspectral imagi…
ClusteringImage SegmentationObjectobject-detection+6RGBD Salient Object Detection via Deep Fusion
Numerous efforts have been made to design different low level saliency cues for the RGBD saliency detection, such as color or depth contrast features, background and color compactness priors. However, how these saliency …
Objectobject-detectionObject DetectionRGB-D Salient Object Detection+3Region-Based Multiscale Spatiotemporal Saliency for Video
Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where …
Saliency Detection