Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation
The deficiency of segmentation labels is one of the main obstacles to semantic
segmentation in the wild. To alleviate this issue, we present a novel framework that …
segmentation in the wild. To alleviate this issue, we present a novel framework that …
Towards high-resolution salient object detection
Deep neural network based methods have made a significant breakthrough in salient object
detection. However, they are typically limited to input images with low resolutions (400x400 …
detection. However, they are typically limited to input images with low resolutions (400x400 …
Part-object relational visual saliency
Recent years have witnessed a big leap in automatic visual saliency detection attributed to
advances in deep learning, especially Convolutional Neural Networks (CNNs). However …
advances in deep learning, especially Convolutional Neural Networks (CNNs). However …
Box2mask: Weakly supervised 3d semantic instance segmentation using bounding boxes
Current 3D segmentation methods heavily rely on large-scale point-cloud datasets, which
are notoriously laborious to annotate. Few attempts have been made to circumvent the need …
are notoriously laborious to annotate. Few attempts have been made to circumvent the need …
Joint fully convolutional and graph convolutional networks for weakly-supervised segmentation of pathology images
Tissue/region segmentation of pathology images is essential for quantitative analysis in
digital pathology. Previous studies usually require full supervision (eg, pixel-level …
digital pathology. Previous studies usually require full supervision (eg, pixel-level …
Weakly supervised semantic segmentation via alternate self-dual teaching
Weakly supervised semantic segmentation (WSSS) is a challenging yet important research
field in vision community. In WSSS, the key problem is to generate high-quality pseudo …
field in vision community. In WSSS, the key problem is to generate high-quality pseudo …
SAL: Selection and attention losses for weakly supervised semantic segmentation
Training a fully supervised semantic segmentation network requires a large amount of
expensive pixel-level annotations in manual labor. In this work, we focus on studying the …
expensive pixel-level annotations in manual labor. In this work, we focus on studying the …
Saliency guided deep network for weakly-supervised image segmentation
F Sun, W Li - Pattern Recognition Letters, 2019 - Elsevier
Weakly-supervised image segmentation is an important task in computer vision. A key
problem is how to obtain high-quality objects location from an image-level category …
problem is how to obtain high-quality objects location from an image-level category …
Singing voice separation using a deep convolutional neural network trained by ideal binary mask and cross entropy
Separating a singing voice from its music accompaniment remains an important challenge in
the field of music information retrieval. We present a unique neural network approach …
the field of music information retrieval. We present a unique neural network approach …