相关论文: No Label Left Behind: A Unified Surface Defect Det…

In semi-supervised learning, methods that rely on confidence learning to generate pseudo-labels have been widely proposed. However, increasing research finds that when faced with noisy and biased data, the model's representation network is…

Machine unlearning aims to remove information derived from forgotten data while preserving that of the remaining dataset in a well-trained model. With the increasing emphasis on data privacy, several approaches to machine unlearning have…

Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…

The bottleneck in learning-based industrial defect detection is often limited not by model capacity, but by the scarcity of labeled defect data: defects are rare, annotations are expensive, and collecting balanced training sets is slow. We…

Time Series Forecasting (TSF) is a crucial task in various domains, yet existing TSF models rely heavily on high-quality data and insufficiently exploit all available data. This paper explores a novel self-supervised approach to re-label…

Supervised machine learning provides state-of-the-art solutions to a wide range of computer vision problems. However, the need for copious labelled training data limits the capabilities of these algorithms in scenarios where such input is…

Recent semi-supervised anomaly detection methods that are trained using small labeled anomaly examples and large unlabeled data (mostly normal data) have shown largely improved performance over unsupervised methods. However, these methods…

Semi-supervised learning has substantially advanced medical image segmentation since it alleviates the heavy burden of acquiring the costly expert-examined annotations. Especially, the consistency-based approaches have attracted more…

Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant…

In this study, we propose a novel motif-based approach for unsupervised textile anomaly detection that combines the benefits of traditional convolutional neural networks with those of an unsupervised learning paradigm. It consists of five…

Lane detection has evolved highly functional autonomous driving system to understand driving scenes even under complex environments. In this paper, we work towards developing a generalized computer vision system able to detect lanes without…

Salient instance segmentation is a new challenging task that received widespread attention in the saliency detection area. The new generation of saliency detection provides a strong theoretical and technical basis for video surveillance.…

Deep learning is pushing the state-of-the-art in many computer vision applications. However, it relies on large annotated data repositories, and capturing the unconstrained nature of the real-world data is yet to be solved. Semi-supervised…

Imperfect labels are ubiquitous in real-world datasets and seriously harm the model performance. Several recent effective methods for handling noisy labels have two key steps: 1) dividing samples into cleanly labeled and wrongly labeled…

Annotation scarcity has become a major obstacle for training powerful deep-learning models for medical image segmentation, restricting their deployment in clinical scenarios. To address it, semi-supervised learning by exploiting abundant…

Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc. However, pretraining is not widely used for 3D recognition tasks where…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from limited labeled examples. Numerous methods for this task focus on utilizing the predictions of unlabeled instances consistency alone to…

Surface inspection systems are an important application domain for computer vision, as they are used for defect detection and classification in the manufacturing industry. Existing systems use hand-crafted features which require extensive…

While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress. To address this, new label-sets and…

Semi-supervised learning methods are motivated by the availability of large datasets with unlabeled features in addition to labeled data. Unlabeled data is, however, not guaranteed to improve classification performance and has in fact been…