Related papers: Cross Pseudo-Labeling for Semi-Supervised Audio-Vi…

Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language. Specifically, self-training, or pseudo-labeling, labels unsupervised data and adds that to the training pool.…

Deep learning with noisy labels is a challenging task. Recent prominent methods that build on a specific sample selection (SS) strategy and a specific semi-supervised learning (SSL) model achieved state-of-the-art performance. Intuitively,…

This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images. Most existing similarity learning methods exacerbate the unexplainability by mapping each…

Due to the high annotation cost of large-scale facial landmark detection tasks in videos, a semi-supervised paradigm that uses self-training for mining high-quality pseudo-labels to participate in training has been proposed by researchers.…

Detecting sound source objects within visual observation is important for autonomous robots to comprehend surrounding environments. Since sounding objects have a large variety with different appearances in our living environments, labeling…

The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks. However, like other modern SSL algorithms, FixMatch uses a pre-defined constant threshold for all classes to select…

Frame-level micro- and macro-expression spotting methods require time-consuming frame-by-frame observation during annotation. Meanwhile, video-level spotting lacks sufficient information about the location and number of expressions during…

Self-training is a simple yet effective method for semi-supervised learning, during which pseudo-label selection plays an important role for handling confirmation bias. Despite its popularity, applying self-training to landmark detection…

Semi-supervised learning has been well developed to help reduce the cost of manual labelling by exploiting a large quantity of unlabelled data. Especially in the application of land cover classification, pixel-level manual labelling in…

While computer vision and machine learning have made great progress, their robustness is still challenged by two key issues: data distribution shift and label noise. When domain generalization (DG) encounters noise, noisy labels further…

Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To…

Domain adaptation helps transfer the knowledge gained from a labeled source domain to an unlabeled target domain. During the past few years, different domain adaptation techniques have been published. One common flaw of these approaches is…

Semi-supervised learning (SSL) has been extensively studied to improve the generalization ability of deep neural networks for visual recognition. To involve the unlabelled data, most existing SSL methods are based on common density-based…

Our objective is to transform a video into a set of discrete audio-visual objects using self-supervised learning. To this end, we introduce a model that uses attention to localize and group sound sources, and optical flow to aggregate…

Image-based 3D detection is an indispensable component of the perception system for autonomous driving. However, it still suffers from the unsatisfying performance, one of the main reasons for which is the limited training data.…

Multi-label image recognition with partial labels (MLR-PL) is designed to train models using a mix of known and unknown labels. Traditional methods rely on semantic or feature correlations to create pseudo-labels for unidentified labels…

Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudolabels, i.e.,…

Pseudo labeling (PL) is a wide-applied strategy to enlarge the labeled dataset by self-annotating the potential samples during the training process. Several works have shown that it can improve the graph learning model performance in…

Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent years, where existing approaches focus on self-training that…

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…