Related papers: Pseudo-label Refinement for Improving Self-Supervi…
Human-annotated vision datasets inevitably contain a fraction of human mislabelled examples. While the detrimental effects of such mislabelling on supervised learning are well-researched, their influence on Supervised Contrastive Learning…
Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…
Training neural networks using limited annotations is an important problem in the medical domain. Deep Neural Networks (DNNs) typically require large, annotated datasets to achieve acceptable performance which, in the medical domain, are…
Recent works on unsupervised domain adaptation (UDA) focus on the selection of good pseudo-labels as surrogates for the missing labels in the target data. However, source domain bias that deteriorates the pseudo-labels can still exist since…
Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…
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…
Fully-unsupervised Person and Vehicle Re-Identification have received increasing attention due to their broad applicability in surveillance, forensics, event understanding, and smart cities, without requiring any manual annotation. However,…
Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically relying on one or…
For an image query, unsupervised contrastive learning labels crops of the same image as positives, and other image crops as negatives. Although intuitive, such a native label assignment strategy cannot reveal the underlying semantic…
Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance. However, the process of collecting and labeling such data can be expensive and time-consuming. Self-supervised…
To alleviate human efforts from obtaining large-scale annotations, Semi-Supervised Relation Extraction methods aim to leverage unlabeled data in addition to learning from limited samples. Existing self-training methods suffer from the…
Current lifelong person re-identification (LReID) methods predominantly rely on fully labeled data streams. However, in real-world scenarios where annotation resources are limited, a vast amount of unlabeled data coexists with scarce…
The problem of fully supervised classification is that it requires a tremendous amount of annotated data, however, in many datasets a large portion of data is unlabeled. To alleviate this problem semi-supervised learning (SSL) leverages the…
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…
Deep learning based semi-supervised learning (SSL) algorithms have led to promising results in recent years. However, they tend to introduce multiple tunable hyper-parameters, making them less practical in real SSL scenarios where the…
Unsupervised Domain Adaptive (UDA) person re-identification (ReID) aims at adapting the model trained on a labeled source-domain dataset to a target-domain dataset without any further annotations. Most successful UDA-ReID approaches combine…
Pre-trained code models have recently achieved substantial improvements in many code intelligence tasks. These models are first pre-trained on large-scale unlabeled datasets in a task-agnostic manner using self-supervised learning, and then…
Multi-label learning is a challenging computer vision task that requires assigning multiple categories to each image. However, fully annotating large-scale datasets is often impractical due to high costs and effort, motivating the study of…
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…
We investigate the mechanisms of self-distillation in multi-class classification, particularly in the context of linear probing with fixed feature extractors where traditional feature learning explanations do not apply. Our theoretical…