Related papers: Refining Pseudo Labels with Clustering Consensus o…
While supervised techniques in re-identification are extremely effective, the need for large amounts of annotations makes them impractical for large camera networks. One-shot re-identification, which uses a singular labeled tracklet for…
Person re-identification aims to establish the correct identity correspondences of a person moving through a non-overlapping multi-camera installation. Recent advances based on deep learning models for this task mainly focus on supervised…
Unsupervised Deep Distance Metric Learning (UDML) aims to learn sample similarities in the embedding space from an unlabeled dataset. Traditional UDML methods usually use the triplet loss or pairwise loss which requires the mining of…
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…
Recent advances in person re-identification have demonstrated enhanced discriminability, especially with supervised learning or transfer learning. However, since the data requirements---including the degree of data curations---are becoming…
Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…
Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions. However, such response maps generated by the classification network usually focus on…
Semi-supervised learning for LiDAR semantic segmentation often suffers from error propagation and confirmation bias caused by noisy pseudo-labels. To tackle this chronic issue, we introduce RePL, a novel framework that enhances pseudo-label…
Utilizing the pseudo-labeling algorithm with large-scale unlabeled data becomes crucial for semi-supervised domain adaptation in speaker verification tasks. In this paper, we propose a novel pseudo-labeling method named Multi-objective…
Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled. To propagate information from the labeled objects to the unlabeled ones, pseudo-labels for unlabeled…
We present a novel clustering objective that learns a neural network classifier from scratch, given only unlabelled data samples. The model discovers clusters that accurately match semantic classes, achieving state-of-the-art results in…
This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to unlabeled data before re-training the model with a…
In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning. We notice that most existing consistency-based approaches suffer from overfitting and limited model generalization ability, especially when…
Recently, Semi-Supervised Learning (SSL) has shown much promise in leveraging unlabeled data while being provided with very few labels. In this paper, we show that ignoring the labels altogether for whole epochs intermittently during…
Previous endeavors in self-supervised learning have enlightened the research of deep clustering from an instance discrimination perspective. Built upon this foundation, recent studies further highlight the importance of grouping…
Noisy labels can negatively impact the performance of deep neural networks. One common solution is label refurbishment, which involves reconstructing noisy labels through predictions and distributions. However, these methods may introduce…
Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data. However, in the context of semi-supervised multi-label learning (SSMLL), conventional pseudo-labeling methods encounter difficulties when dealing…
Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a…
Self-training (ST) is a simple yet effective semi-supervised learning method. However, why and how ST improves generalization performance by using potentially erroneous pseudo-labels is still not well understood. To deepen the understanding…
Recently unsupervised person re-identification (re-ID) has drawn much attention due to its open-world scenario settings where limited annotated data is available. Existing supervised methods often fail to generalize well on unseen domains,…