Related papers: Neighbor-aware Instance Refining with Noisy Labels…
Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been…
Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by leveraging clustering-based pseudo labels, but these pseudo…
Cross-modal noise-robust learning is a challenging task since noisy correspondence is hard to recognize and rectify. Due to the cumulative and unavoidable negative impact of unresolved noise, existing methods cannot maintain a stable…
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness to noisy labels in classification tasks, the problem of…
Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…
Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global noise estimation and data filtering. Global noise…
Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current learning methods based on the clean label assumptions may fail with noisy labels. Yet, class…
The success of Deep Neural Network (DNN) models significantly depends on the quality of provided annotations. In medical image segmentation, for example, having multiple expert annotations for each data point is common to minimize…
We explore the potential of large-scale noisily labeled data to enhance feature learning by pretraining semantic segmentation models within a multi-modal framework for geospatial applications. We propose a novel Cross-modal Sample Selection…
As a promising solution of reducing annotation cost, training multi-label models with partial positive labels (MLR-PPL), in which merely few positive labels are known while other are missing, attracts increasing attention. Due to the…
Deep convolutional neural networks (CNNs) learned on large-scale labeled samples have achieved remarkable progress in computer vision, such as image/video classification. The cheapest way to obtain a large body of labeled visual data is to…
Learning with noisy labels (LNL) aims to ensure model generalization given a label-corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine-grained datasets (LNL-FG), which is more practical and…
In noisy label learning, estimating noisy class posteriors plays a fundamental role for developing consistent classifiers, as it forms the basis for estimating clean class posteriors and the transition matrix. Existing methods typically…
Despite the recent developments in the field of cross-modal retrieval, there has been less research focusing on low-resource languages due to the lack of manually annotated datasets. In this paper, we propose a noise-robust cross-lingual…
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…
Foundation models (FMs) pretrained on large datasets have become fundamental for various downstream machine learning tasks, in particular in scenarios where obtaining perfectly labeled data is prohibitively expensive. In this paper, we…
Learning with Noisy Labels (LNL) has attracted significant attention from the research community. Many recent LNL methods rely on the assumption that clean samples tend to have "small loss". However, this assumption always fails to…
Deep Metric Learning (DML) plays a critical role in various machine learning tasks. However, most existing deep metric learning methods with binary similarity are sensitive to noisy labels, which are widely present in real-world data. Since…
Collecting a large number of reliable training images annotated by multiple land-cover class labels in the framework of multi-label classification is time-consuming and costly in remote sensing (RS). To address this problem, publicly…
Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world…