Adversarial training has been shown to produce state of the art results for generative image
modeling. In this paper we propose an adversarial training approach to train semantic …

CNN architectures have terrific recognition performance but rely on spatial pooling which
makes it difficult to adapt them to tasks that require dense, pixel-accurate labeling. This …

In recent years, we have seen tremendous progress in the field of object detection. Most of
the recent improvements have been achieved by targeting deeper feedforward networks …

Deep learning has considerably improved semantic image segmentation. However, its high
accuracy is traded against larger computational costs which makes it unsuit-able for …

The recent COCO object detection dataset presents several new challenges for object
detection. In particular, it contains objects at a broad range of scales, less prototypical …

Inspired by recent advances of deep learning in instance segmentation and object tracking,
we introduce video object segmentation problem as a concept of guided instance …

State-of-the-art image segmentation algorithms generally consist of at least two successive
and distinct computations: a boundary detection process that uses local image information to …

We address the problem of instance-level semantic segmentation, which aims at jointly
detecting, segmenting and classifying every individual object in an image. In this context …

Instance segmentation has attracted recent attention in computer vision and existing
methods in this domain mostly have an object detection stage. In this paper, we study the …

In this paper, we propose a new image instance segmentation method that segments
individual glands (instances) in colon histology images. This is a task called instance …