Related papers: SePiCo: Semantic-Guided Pixel Contrast for Domain …

Whilst contrastive learning has recently brought notable benefits to deep clustering of unlabelled images by learning sample-specific discriminative visual features, its potential for explicitly inferring class decision boundaries is less…

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to…

Domain adaptation manages to transfer the knowledge of well-labeled source data to unlabeled target data. Many recent efforts focus on improving the prediction accuracy of target pseudo-labels to reduce conditional distribution shift. In…

Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets.…

This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…

Recently, semantic parsing has attracted much attention in the community. Although many neural modeling efforts have greatly improved the performance, it still suffers from the data scarcity issue. In this paper, we propose a novel semantic…

We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage…

Impressive image captioning results are achieved in domains with plenty of training image and sentence pairs (e.g., MSCOCO). However, transferring to a target domain with significant domain shifts but no paired training data (referred to as…

Training deep networks for semantic segmentation requires annotation of large amounts of data, which can be time-consuming and expensive. Unfortunately, these trained networks still generalize poorly when tested in domains not consistent…

Semantic segmentation of remote sensing (RS) images is a challenging yet essential task with broad applications. While deep learning, particularly supervised learning with large-scale labeled datasets, has significantly advanced this field,…

Hyperspectral image (HSI) clustering is gaining considerable attention owing to recent methods that overcome the inefficiency and misleading results from the absence of supervised information. Contrastive learning methods excel at existing…

Semi-supervised semantic segmentation learns a model for classifying pixels into specific classes using a few labeled samples and numerous unlabeled images. The recent leading approach is consistency regularization by selftraining with…

Pseudo-labeling is a key component in semi-supervised learning (SSL). It relies on iteratively using the model to generate artificial labels for the unlabeled data to train against. A common property among its various methods is that they…

Image captioning models are becoming increasingly successful at describing the content of images in restricted domains. However, if these models are to function in the wild - for example, as assistants for people with impaired vision - a…

Most machine vision tasks (e.g., semantic segmentation) are based on images encoded and decoded by image compression algorithms (e.g., JPEG). However, these decoded images in the pixel domain introduce distortion, and they are optimized for…

In previous deep-learning-based methods, semantic segmentation has been regarded as a static or dynamic per-pixel classification task, \textit{i.e.,} classify each pixel representation to a specific category. However, these methods only…

Referring image segmentation aims to segment a referent via a natural linguistic expression.Due to the distinct data properties between text and image, it is challenging for a network to well align text and pixel-level features. Existing…

The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class…

We present a new semi-supervised domain adaptation framework that combines a novel auto-encoder-based domain adaptation model with a simultaneous learning scheme providing stable improvements over state-of-the-art domain adaptation models.…

Semantic segmentation is one of the basic topics in computer vision, it aims to assign semantic labels to every pixel of an image. Unbalanced semantic label distribution could have a negative influence on segmentation accuracy. In this…