Related papers: Reliability-Adaptive Consistency Regularization fo…

The development of reliable methods for multi-label classification (MLC) has become a prominent research direction in remote sensing (RS). As the scale of RS data continues to expand, annotation procedures increasingly rely on thematic…

We propose a weakly supervised semantic segmentation method for point clouds that predicts "per-point" labels from just "whole-scene" annotations. The key challenge here is the discrepancy between the target of dense per-point semantic…

Point cloud classification is a popular task in 3D vision. However, previous works, usually assume that point clouds at test time are obtained with the same procedure or sensor as those at training time. Unsupervised Domain Adaptation (UDA)…

3D Referring Expression Segmentation (3D-RES) typically requires extensive instance-level annotations, which are time-consuming and costly. Semi-supervised learning (SSL) mitigates this by using limited labeled data alongside abundant…

Generative Adversarial Networks (GANs) based semi-supervised learning (SSL) approaches are shown to improve classification performance by utilizing a large number of unlabeled samples in conjunction with limited labeled samples. However,…

Deep learning algorithms have obtained great success in semantic segmentation of very high-resolution (VHR) images. Nevertheless, training these models generally requires a large amount of accurate pixel-wise annotations, which is very…

Semantic segmentation has been continuously investigated in the last ten years, and majority of the established technologies are based on supervised models. In recent years, image-level weakly supervised semantic segmentation (WSSS),…

Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In…

Point supervision has become a scalable solution to address dense annotation for infrared small target detection, but its performance is limited by two coupled bottlenecks: unstable pseudo-label evolution in cluttered, low-contrast infrared…

Unsupervised domain adaptation aiming to learn a specific task for one domain using another domain data has emerged to address the labeling issue in supervised learning, especially because it is difficult to obtain massive amounts of…

Outdoor LiDAR point cloud 3D instance segmentation is a crucial task in autonomous driving. However, it requires laborious human efforts to annotate the point cloud for training a segmentation model. To address this challenge, we propose a…

Consistency regularization and pseudo-labeling have significantly advanced semi-supervised learning (SSL). Prior works have effectively employed Mixup for consistency regularization in SSL. However, our findings indicate that applying Mixup…

The task of parsing subcutaneous vessels in clinical images is often hindered by the high cost and limited availability of ground truth data, as well as the challenge of low contrast and noisy vessel appearances across different patients…

In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semi-supervised learning framework for leveraging unlabeled data under the…

In this paper, we propose a novel framework that combines ensemble learning with augmented graph structures to improve the performance and robustness of semi-supervised node classification in graphs. By creating multiple augmented views of…

The annotation of 3D datasets is required for semantic-segmentation and object detection in scene understanding. In this paper we present a framework for the weakly supervision of a point clouds transformer that is used for 3D object…

Point cloud anomaly detection under the anomaly-free setting poses significant challenges as it requires accurately capturing the features of 3D normal data to identify deviations indicative of anomalies. Current efforts focus on devising…

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…

Instance segmentation on 3D point clouds has been attracting increasing attention due to its wide applications, especially in scene understanding areas. However, most existing methods operate on fully annotated data while manually preparing…

In this paper, we propose a novel mutual consistency network (MC-Net+) to effectively exploit the unlabeled data for semi-supervised medical image segmentation. The MC-Net+ model is motivated by the observation that deep models trained with…