Related papers: Learning Multiple Representations with Inconsisten…

Learning object segmentation in image and video datasets without human supervision is a challenging problem. Humans easily identify moving salient objects in videos using the gestalt principle of common fate, which suggests that what moves…

Self-attention is of vital importance in semantic segmentation as it enables modeling of long-range context, which translates into improved performance. We argue that it is equally important to model short-range context, especially to…

We propose a machine learning based approach for automatic regularization and polygonization of building segmentation masks. Taking an image as input, we first predict building segmentation maps exploiting generic fully convolutional…

A major bottleneck in the real-world applications of machine learning models is their failure in generalizing to unseen domains whose data distribution is not i.i.d to the training domains. This failure often stems from learning…

Visual change detection, aiming at segmentation of video frames into foreground and background regions, is one of the elementary tasks in computer vision and video analytics. The applications of change detection include anomaly detection,…

This paper presents a "learning to learn" approach to figure-ground image segmentation. By exploring webly-abundant images of specific visual effects, our method can effectively learn the visual-effect internal representations in an…

Unsupervised anomaly detection in brain imaging is challenging. In this paper, we propose self-supervised masked mesh learning for unsupervised anomaly detection on 3D cortical surfaces. Our framework leverages the intrinsic geometry of the…

Fine-grained image recognition has been a hot research topic in computer vision due to its various applications. The-state-of-the-art is the part/region-based approaches that first localize discriminative parts/regions, and then learn their…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…

In this paper, we propose a novel end-to-end unsupervised deep domain adaptation model for adaptive object detection by exploiting multi-label object recognition as a dual auxiliary task. The model exploits multi-label prediction to reveal…

Unsupervised feature learning often finds low-dimensional embeddings that capture the structure of complex data. For tasks for which prior expert topological knowledge is available, incorporating this into the learned representation may…

Most image labeling problems such as segmentation and image reconstruction are fundamentally ill-posed and suffer from ambiguities and noise. Higher order image priors encode high level structural dependencies between pixels and are key to…

Many existing learning-based grasping approaches concentrate on a single embodiment, provide limited generalization to higher DoF end-effectors and cannot capture a diverse set of grasp modes. We tackle the problem of grasping using…

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training approach in the vision domain. However, the mechanism and properties of the learned representations by such a scheme, as well as how to further enhance…

Natural image matting is an important problem in computer vision and graphics. It is an ill-posed problem when only an input image is available without any external information. While the recent deep learning approaches have shown promising…

Text detection, the key technology for understanding scene text, has become an attractive research topic. For detecting various scene texts, researchers propose plenty of detectors with different advantages: detection-based models enjoy…

Unsupervised visual anomaly detection is crucial for enhancing industrial production quality and efficiency. Among unsupervised methods, reconstruction approaches are popular due to their simplicity and effectiveness. The key aspect of…

Text segmentation tasks have a very wide range of application values, such as image editing, style transfer, watermark removal, etc.However, existing public datasets are of poor quality of pixel-level labels that have been shown to be…

Standard losses for training deep segmentation networks could be seen as individual classifications of pixels, instead of supervising the global shape of the predicted segmentations. While effective, they require exact knowledge of the…