相关论文: SELECT: Detecting Label Errors in Real-world Scene…

Supervised learning is based on the assumption that the ground truth in the training data is accurate. However, this may not be guaranteed in real-world settings. Inaccurate training data will result in some unexpected predictions. In image…

The prevalent perspectives of scene text recognition are from sequence to sequence (seq2seq) and segmentation. Nevertheless, the former is composed of many components which makes implementation and deployment complicated, while the latter…

Semi-supervised object detection has recently achieved substantial progress. As a mainstream solution, the self-labeling-based methods train the detector on both labeled data and unlabeled data with pseudo labels predicted by the detector…

Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Compared with image scene parsing, video scene parsing…

Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications. State-of-the-art recurrent neural networks (RNN) based models map an input…

Our daily life is surrounded by textual information. Nowadays, the automatic collection of textual information becomes possible owing to the drastic improvement of scene text detectors and recognizer. The purpose of this paper is to conduct…

In learning tasks with label noise, improving model robustness against overfitting is a pivotal challenge because the model eventually memorizes labels, including the noisy ones. Identifying the samples with noisy labels and preventing the…

This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective. We begin by revisiting the six commonly used benchmarks in STR and observe a trend of performance saturation, whereby only 2.91% of the benchmark…

Scene text recognition has attracted great interests from the computer vision and pattern recognition community in recent years. State-of-the-art methods use concolutional neural networks (CNNs), recurrent neural networks with long…

Video action segmentation under timestamp supervision has recently received much attention due to lower annotation costs. Most existing methods generate pseudo-labels for all frames in each video to train the segmentation model. However,…

Semi-supervised learning (SSL) is one of the dominant approaches to address the annotation bottleneck of supervised learning. Recent SSL methods can effectively leverage a large repository of unlabeled data to improve performance while…

We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have shown impressive…

The label quality of defect data sets has a direct influence on the reliability of defect prediction models. In this study, for multi-version-project defect data sets, we propose an approach to automatically detecting instances with…

The recent large-scale Contrastive Language-Image Pretraining (CLIP) model has shown great potential in various downstream tasks via leveraging the pretrained vision and language knowledge. Scene text, which contains rich textual and visual…

Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples…

Annotation quality and quantity positively affect the learning performance of sequence labeling, a vital task in Natural Language Processing. Hiring domain experts to annotate a corpus is very costly in terms of money and time.…

We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently…

Learning from noisy data has attracted much attention, where most methods focus on closed-set label noise. However, a more common scenario in the real world is the presence of both open-set and closed-set noise. Existing methods typically…

Contrastive Language Image Pre-training (CLIP) has recently demonstrated success across various tasks due to superior feature representation empowered by image-text contrastive learning. However, the instance discrimination method used by…

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…