Related papers: Optimizing against Infeasible Inclusions from Data…
Interactive segmentation allows efficient label generation by leveraging user-provided clicks to progressively refine predictions, which is critical when fully supervised labels are costly or generalization to unseen classes is needed.…
This paper addresses the task of zero-shot image classification. The key contribution of the proposed approach is to control the semantic embedding of images -- one of the main ingredients of zero-shot learning -- by formulating it as a…
This paper presents a novel method for discovering systematic errors in segmentation models. For instance, a systematic error in the segmentation model can be a sufficiently large number of misclassifications from the model as a parking…
Despite the remarkable success of deep learning in medical imaging analysis, medical image segmentation remains challenging due to the scarcity of high-quality labeled images for supervision. Further, the significant domain gap between…
Deep neural networks are powerful tools for biomedical image segmentation. These models are often trained with heavy supervision, relying on pairs of images and corresponding voxel-level labels. However, obtaining segmentations of…
Semantic segmentation is the task of classifying each pixel in an image. Training a segmentation model achieves best results using annotated images, where each pixel is annotated with the corresponding class. When obtaining fine annotations…
Semantic segmentation for autonomous driving is an even more challenging task when faced with adverse driving conditions. Standard models trained on data recorded under ideal conditions show a deteriorated performance in unfavorable weather…
All classifiers, including state-of-the-art vision models, possess invariants, partially rooted in the geometry of their linear mappings. These invariants, which reside in the null-space of the classifier, induce equivalent sets of inputs…
Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…
Semantic segmentation is a crucial task in medical imaging. Although supervised learning techniques have proven to be effective in performing this task, they heavily depend on large amounts of annotated training data. The recently…
For the semantic segmentation of images, state-of-the-art deep neural networks (DNNs) achieve high segmentation accuracy if that task is restricted to a closed set of classes. However, as of now DNNs have limited ability to operate in an…
Semantic segmentation takes pivotal roles in various applications such as autonomous driving and medical image analysis. When deploying segmentation models in practice, it is critical to test their behaviors in varied and complex scenes in…
Removing supervision in semantic segmentation is still tricky. Current approaches can deal with common categorical patterns yet resort to multi-stage architectures. We design a novel end-to-end model leveraging local-global patch matching…
Introducing explicit constraints on the structural predictions has been an effective way to improve the performance of semantic segmentation models. Existing methods are mainly based on insufficient hand-crafted rules that only partially…
Finetuning a pretrained backbone in the encoder part of an image transformer network has been the traditional approach for the semantic segmentation task. However, such an approach leaves out the semantic context that an image provides…
Semantic segmentation is one of the basic, yet essential scene understanding tasks for an autonomous agent. The recent developments in supervised machine learning and neural networks have enjoyed great success in enhancing the performance…
Semi-supervised semantic segmentation aims to utilize limited labeled images and abundant unlabeled images to achieve label-efficient learning, wherein the weak-to-strong consistency regularization framework, popularized by FixMatch, is…
Semi-supervised learning (SSL) for medical image segmentation is a challenging yet highly practical task, which reduces reliance on large-scale labeled dataset by leveraging unlabeled samples. Among SSL techniques, the weak-to-strong…
The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and…
Semantic image inpainting is a challenging task where large missing regions have to be filled based on the available visual data. Existing methods which extract information from only a single image generally produce unsatisfactory results…