Related papers: Exploiting Web Images for Fine-Grained Visual Reco…

Learning an empirically effective model with generalization using limited data is a challenging task for deep neural networks. In this paper, we propose a novel learning framework called PurifiedLearning to exploit task-irrelevant features…

As an open research topic in the field of deep learning, learning with noisy labels has attracted much attention and grown rapidly over the past ten years. Learning with label noise is crucial for driver distraction behavior recognition, as…

Noisy Labels are commonly present in data sets automatically collected from the internet, mislabeled by non-specialist annotators, or even specialists in a challenging task, such as in the medical field. Although deep learning models have…

The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation of the data is impractical; instead our data has noisy labels, i.e.…

In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is…

Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the…

Despite remarkable progress on visual recognition tasks, deep neural-nets still struggle to generalize well when training data is scarce or highly imbalanced, rendering them extremely vulnerable to real-world examples. In this paper, we…

In recent years, deep neural networks (DNNs) have gained remarkable achievement in computer vision tasks, and the success of DNNs often depends greatly on the richness of data. However, the acquisition process of data and high-quality…

In this dissertation, we propose a systemic framework that prioritizes informative features and examples to enhance each stage of the development process. Specifically, we prioritize informative features and examples and improve the…

Learning an object detector or retrieval requires a large data set with manual annotations. Such data sets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose to exploit…

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real…

This paper considers recognizing products from daily photos, which is an important problem in real-world applications but also challenging due to background clutters, category diversities, noisy labels, etc. We address this problem by two…

We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to…

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise,…

Deep neural networks have incredible capacity and expressibility, and can seemingly memorize any training set. This introduces a problem when training in the presence of noisy labels, as the noisy examples cannot be distinguished from clean…

Fine-grained annotations---e.g. dense image labels, image segmentation and text tagging---are useful in many ML applications but they are labor-intensive to generate. Moreover there are often systematic, structured errors in these…

Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…

Current methods focusing on medical image segmentation suffer from incorrect annotations, which is known as the noisy label issue. Most medical image segmentation with noisy labels methods utilize either noise transition matrix,…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data. However, the quality of data labels is a concern because of the lack of high-quality labels in many real-world scenarios. As noisy…