Related papers: PCSR: Pseudo-label Consistency-Guided Sample Refin…

Designing robust algorithms capable of training accurate neural networks on uncurated datasets from the web has been the subject of much research as it reduces the need for time consuming human labor. The focus of many previous research…

Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly degrades the performance of SSOD methods. Recent advances…

Unsupervised person re-identification (re-ID) aims at learning discriminative representations for person retrieval from unlabeled data. Recent techniques accomplish this task by using pseudo-labels, but these labels are inherently noisy and…

In the realm of cross-modal retrieval, seamlessly integrating diverse modalities within multimedia remains a formidable challenge, especially given the complexities introduced by noisy correspondence learning (NCL). Such noise often stems…

Acquiring accurate labels on large-scale datasets is both time consuming and expensive. To reduce the dependency of deep learning models on learning from clean labeled data, several recent research efforts are focused on learning with noisy…

As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space. To achieve this, massive and correctly aligned data pairs are required for model…

In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object…

Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. Recently, to alleviate expensive data collection, co-occurring pairs from the Internet are automatically harvested for training. However, it…

Label noise is a common issue in real-world datasets that inevitably impacts the generalization of models. This study focuses on robust classification tasks where the label noise is instance-dependent. Estimating the transition matrix…

Noisy label learning aims to train deep neural networks using a large amount of samples with noisy labels, whose main challenge comes from how to deal with the inaccurate supervision caused by wrong labels. Existing works either take the…

Despite the success of multimodal learning in cross-modal retrieval task, the remarkable progress relies on the correct correspondence among multimedia data. However, collecting such ideal data is expensive and time-consuming. In practice,…

In recent years, Cross-Modal Retrieval (CMR) has made significant progress in the field of multi-modal analysis. However, since it is time-consuming and labor-intensive to collect large-scale and well-annotated data, the annotation of…

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…

Recently, the usage of Contrastive Representation Learning (CRL) as a pre-training technique improves the performance of learning with noisy labels (LNL) methods. However, instead of pre-training, when trivially combining CRL loss with LNL…

Semantic segmentation of SAR images has garnered significant attention in remote sensing due to the immunity of SAR sensors to cloudy weather and light conditions. Nevertheless, SAR imagery lacks detailed information and is plagued by…

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…

We motivate weakly supervised learning as an effective learning paradigm for problems where curating perfectly annotated datasets is expensive and may require domain expertise such as fine-grained classification. We focus on Partial Label…

Pseudo-labeling is a commonly used paradigm in semi-supervised learning, yet its application to semi-supervised regression (SSR) remains relatively under-explored. Unlike classification, where pseudo-labels are discrete and confidence-based…

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection…

Partial-label learning (PLL) is an important weakly supervised learning problem, which allows each training example to have a candidate label set instead of a single ground-truth label. Identification-based methods have been widely explored…