Related papers: Understanding Imbalanced Semantic Segmentation Thr…
The modern strategy for training deep neural networks for classification tasks includes optimizing the network's weights even after the training error vanishes to further push the training loss toward zero. Recently, a phenomenon termed…
Deep classifier neural networks enter the terminal phase of training (TPT) when training error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural collapse essentially represents a state at which the…
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 is a computer vision task that associates a label with each pixel in an image. Modern approaches tend to introduce class embeddings into semantic segmentation for deeply utilizing category semantics, and regard…
Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…
The consistency loss has played a key role in solving problems in recent studies on semi-supervised learning. Yet extant studies with the consistency loss are limited to its application to classification tasks; extant studies on…
Class imbalance is a fundamental problem in computer vision applications such as semantic segmentation. Specifically, uneven class distributions in a training dataset often result in unsatisfactory performance on under-represented classes.…
Continual semantic segmentation aims to learn new classes while maintaining the information from the previous classes. Although prior studies have shown impressive progress in recent years, the fairness concern in the continual semantic…
To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning,…
Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…
Semi-supervised semantic segmentation learns from small amounts of labelled images and large amounts of unlabelled images, which has witnessed impressive progress with the recent advance of deep neural networks. However, it often suffers…
Current semantic segmentation methods focus only on mining "local" context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention) or structure-aware…
Semantic segmentation consists of predicting a semantic label for each image pixel. While existing deep learning approaches achieve high accuracy, they often overlook the ordinal relationships between classes, which can provide critical…
Semi-supervised semantic segmentation requires the model to effectively propagate the label information from limited annotated images to unlabeled ones. A challenge for such a per-pixel prediction task is the large intra-class variation,…
A phenomenon known as ''Neural Collapse (NC)'' in deep classification tasks, in which the penultimate-layer features and the final classifiers exhibit an extremely simple geometric structure, has recently attracted considerable attention,…
Data imbalance, in which a plurality of the data samples come from a small proportion of labels, poses a challenge in training deep neural networks. Unlike classification, in regression the labels are continuous, potentially boundless, and…
Class imbalance poses a challenge for developing unbiased, accurate predictive models. In particular, in image segmentation neural networks may overfit to the foreground samples from small structures, which are often heavily…
Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and addresses three common problems: (1) Objects…
Recent studies on semantic communication commonly rely on neural network (NN) based transceivers such as deep joint source and channel coding (DeepJSCC). Unlike traditional transceivers, these neural transceivers are trainable using actual…
Deep neural networks (DNNs) exhibit a surprising structure in their final layer known as neural collapse (NC), and a growing body of works has currently investigated the propagation of neural collapse to earlier layers of DNNs -- a…