Related papers: On the Road to Online Adaptation for Semantic Imag…

Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervision which is expensive and time-consuming. Further, training…

Deep convolutional neural networks (CNNs) have been immensely successful in many high-level computer vision tasks given large labeled datasets. However, for video semantic object segmentation, a domain where labels are scarce, effectively…

Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are…

Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features. This problem is typically…

Action segmentation of behavioral videos is the process of labeling each frame as belonging to one or more discrete classes, and is a crucial component of many studies that investigate animal behavior. A wide range of algorithms exist to…

Unsupervised domain adaptation (UDA) adapts a model trained on one domain (called source) to a novel domain (called target) using only unlabeled data. Due to its high annotation cost, researchers have developed many UDA methods for semantic…

Semantic segmentation aims to robustly predict coherent class labels for entire regions of an image. It is a scene understanding task that powers real-world applications (e.g., autonomous navigation). One important application, the use of…

Semantic image segmentation is one of fastest growing areas in computer vision with a variety of applications. In many areas, such as robotics and autonomous vehicles, semantic image segmentation is crucial, since it provides the necessary…

Although there is significant progress in supervised semantic segmentation, it remains challenging to deploy the segmentation models to unseen domains due to domain biases. Domain adaptation can help in this regard by transferring knowledge…

Panoptic segmentation unifies semantic segmentation and instance segmentation which has been attracting increasing attention in recent years. However, most existing research was conducted under a supervised learning setup whereas…

This paper presents a new regularization method to train a fully convolutional network for semantic tissue segmentation in histopathological images. This method relies on the benefit of unsupervised learning, in the form of image…

Large-scale labeled training datasets have enabled deep neural networks to excel on a wide range of benchmark vision tasks. However, in many applications it is prohibitively expensive or time-consuming to obtain large quantities of labeled…

Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be surprisingly poor under domain shifts that appear mild to a…

Deep learning algorithms have demonstrated tremendous success on challenging medical imaging problems. However, post-deployment, these algorithms are susceptible to data distribution variations owing to \emph{limited data issues} and…

Image semantic segmentation is more and more being of interest for computer vision and machine learning researchers. Many applications on the rise need accurate and efficient segmentation mechanisms: autonomous driving, indoor navigation,…

The recent success of neural machine translation models relies on the availability of high quality, in-domain data. Domain adaptation is required when domain-specific data is scarce or nonexistent. Previous unsupervised domain adaptation…

Many automated processes such as auto-piloting rely on a good semantic segmentation as a critical component. To speed up performance, it is common to downsample the input frame. However, this comes at the cost of missed small objects and…

It is expensive to generate real-life image labels and there is a domain gap between real-life and simulated images, hence a model trained on the latter cannot adapt to the former. Solving this can totally eliminate the need for labeling…

Deep convolutional neural networks (CNNs) have shown excellent performance in object recognition tasks and dense classification problems such as semantic segmentation. However, training deep neural networks on large and sparse datasets is…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…