We introduce a new loss function for the weakly-supervised training of semantic image
segmentation models based on three guiding principles: to seed with weak localization …

Weakly supervised instance segmentation with image-level labels, instead of expensive
pixel-level masks, remains unexplored. In this paper, we tackle this challenging problem by …

As an interesting and emerging topic, co-saliency detection aims at simultaneously
extracting common salient objects from a group of images. On one hand, traditional co …

We present an end-to-end, multimodal, fully convolutional network for extracting semantic
structures from document images. We consider document semantic structure extraction as a …

We address weakly supervised action alignment and segmentation in videos, where only
the order of occurring actions is available during training. We propose Discriminative …

Currently, most mask extraction techniques are based on convolutional neural networks
(CNNs). However, there are still numerous problems that mask extraction techniques need …

State of the art methods for semantic image segmentation are trained in a supervised
fashion using a large corpus of fully labeled training images. However, gathering such a …

The image semantic segmentation has been extensively studying. The modern methods rely
on the deep convolutional neural networks, which can be trained to address this problem. A …

There is an emerging trend to leverage noisy image datasets in many visual recognition
tasks. However, the label noise among datasets severely degenerates the performance of …

Building a large image dataset with high-quality object masks for semantic segmentation is
costly and time-consuming. In this paper, we introduce a principled semi-supervised …