相关论文: Learning without Prejudice: Avoiding Bias in Webly…

Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are limited in providing theoretical guarantees for the performance of the…

The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods often overlook the…

Learning with curriculum has shown great effectiveness in tasks where the data contains noisy (corrupted) labels, since the curriculum can be used to re-weight or filter out noisy samples via proper design. However, obtaining curriculum…

Due to the veracity and heterogeneity in network traffic, detecting anomalous events is challenging. The computational load on global servers is a significant challenge in terms of efficiency, accuracy, and scalability. Our primary…

We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing.…

We present an approach to effectively use millions of images with noisy annotations in conjunction with a small subset of cleanly-annotated images to learn powerful image representations. One common approach to combine clean and noisy data…

In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are lifelong image classification or recognition of environmental objects during interaction of…

Graph Neural Networks (GNNs) have emerged as a powerful tool for representation learning on graphs, but they often suffer from overfitting and label noise issues, especially when the data is scarce or imbalanced. Different from the paradigm…

Deep learning with noisy labels is an interesting challenge in weakly supervised learning. Despite their significant learning capacity, CNNs have a tendency to overfit in the presence of samples with noisy labels. Alleviating this issue,…

Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and…

Supervised learning usually requires a large amount of labelled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some…

Exemplar learning of visual similarities in an unsupervised manner is a problem of paramount importance to Computer Vision. In this context, however, the recent breakthrough in deep learning could not yet unfold its full potential. With…

Supervised training has led to state-of-the-art results in image and video denoising. However, its application to real data is limited since it requires large datasets of noisy-clean pairs that are difficult to obtain. For this reason,…

Webly supervised learning becomes attractive recently for its efficiency in data expansion without expensive human labeling. However, adopting search queries or hashtags as web labels of images for training brings massive noise that…

Current action recognition methods heavily rely on trimmed videos for model training. However, it is expensive and time-consuming to acquire a large-scale trimmed video dataset. This paper presents a new weakly supervised architecture,…

Neural network-based anomaly detection methods have shown to achieve high performance. However, they require a large amount of training data for each task. We propose a neural network-based meta-learning method for supervised anomaly…

The convolution neural nets (conv nets) have achieved a state-of-the-art performance in many applications of image and video processing. The most recent studies illustrate that the conv nets are fragile in terms of recognition accuracy to…

Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…

In this work we address the challenging problem of unsupervised learning from videos. Existing methods utilize the spatio-temporal continuity in contiguous video frames as regularization for the learning process. Typically, this temporal…

Deep Neural Networks (DNNs) have been successfully applied to a wide range of problems. However, two main limitations are commonly pointed out. The first one is that they require long time to design. The other is that they heavily rely on…