Related papers: Learning from Web Data: the Benefit of Unsupervise…

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…

The style of an image plays a significant role in how it is viewed, but style has received little attention in computer vision research. We describe an approach to predicting style of images, and perform a thorough evaluation of different…

Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised counterpart, making their practicability questionable. We…

A recurring focus of the deep learning community is towards reducing the labeling effort. Data gathering and annotation using a search engine is a simple alternative to generating a fully human-annotated and human-gathered dataset. Although…

In the last couple of years, weakly labeled learning has turned out to be an exciting approach for audio event detection. In this work, we introduce webly labeled learning for sound events which aims to remove human supervision altogether…

Convolutional neural network (CNN) models have demonstrated great success in various computer vision tasks including image classification and object detection. However, some equally important tasks such as visual tracking remain relatively…

A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for…

Collecting large training datasets, annotated with high-quality labels, is costly and time-consuming. This paper proposes a novel framework for training deep convolutional neural networks from noisy labeled datasets that can be obtained…

TThe goal of our work is to discover dominant objects in a very general setting where only a single unlabeled image is given. This is far more challenge than typical co-localization or weakly-supervised localization tasks. To tackle this…

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…

Graph-based semi-supervised learning has been shown to be one of the most effective approaches for classification tasks from a wide range of domains, such as image classification and text classification, as they can exploit the connectivity…

Training deep neural networks to estimate the viewpoint of objects requires large labeled training datasets. However, manually labeling viewpoints is notoriously hard, error-prone, and time-consuming. On the other hand, it is relatively…

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…

Reviewing radiology reports in emergency departments is an essential but laborious task. Timely follow-up of patients with abnormal cases in their radiology reports may dramatically affect the patient's outcome, especially if they have been…

Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. Due to the limited…

The impressive advancements in semi-supervised learning have driven researchers to explore its potential in object detection tasks within the field of computer vision. Semi-Supervised Object Detection (SSOD) leverages a combination of a…

Self-supervised learning (SSL) is a scalable way to learn general visual representations since it learns without labels. However, large-scale unlabeled datasets in the wild often have long-tailed label distributions, where we know little…