Related papers: Weakly supervised collective feature learning from…

Neural network approaches have recently shown to be effective in several information retrieval (IR) tasks. However, neural approaches often require large volumes of training data to perform effectively, which is not always available. To…

We study how to leverage Web images to augment human-curated object detection datasets. Our approach is two-pronged. On the one hand, we retrieve Web images by image-to-image search, which incurs less domain shift from the curated data than…

The rapid development of deep learning has driven significant progress in image semantic segmentation - a fundamental task in computer vision. Semantic segmentation algorithms often depend on the availability of pixel-level labels (i.e.,…

Fine-grained image classification involves identifying different subcategories of a class which possess very subtle discriminatory features. Fine-grained datasets usually provide bounding box annotations along with class labels to aid the…

The availability of large-scale data sets is an essential pre-requisite for deep learning based semantic segmentation schemes. Since obtaining pixel-level labels is extremely expensive, supervising deep semantic segmentation networks using…

Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. Intuitively, weakly supervised training is a direct solution to reduce the cost of labeling.…

We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any human annotation. We develop a…

Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, in this paper, we focus on the minimally-supervised setting…

Hierarchical text classification, which aims to classify text documents into a given hierarchy, is an important task in many real-world applications. Recently, deep neural models are gaining increasing popularity for text classification due…

Image clustering is to group a set of images into disjoint clusters in a way that images in the same cluster are more similar to each other than to those in other clusters, which is an unsupervised or semi-supervised learning process. It is…

In this study, a spectral graph-theoretic grouping strategy for weakly supervised classification is introduced, where a limited number of labelled samples and a larger set of unlabelled samples are used to construct a larger annotated…

Curation of large fully supervised datasets has become one of the major roadblocks for machine learning. Weak supervision provides an alternative to supervised learning by training with cheap, noisy, and possibly correlated labeling…

Point cloud analysis has received much attention recently; and segmentation is one of the most important tasks. The success of existing approaches is attributed to deep network design and large amount of labelled training data, where the…

Current weakly-supervised incremental learning for semantic segmentation (WILSS) approaches only consider replacing pixel-level annotations with image-level labels, while the training images are still from well-designed datasets. In this…

Since acquiring pixel-wise annotations for training convolutional neural networks for semantic image segmentation is time-consuming, weakly supervised approaches that only require class tags have been proposed. In this work, we propose…

Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags. Despite intensive research on deep learning approaches over a decade, there is still a significant performance gap…

Training a Fully Convolutional Network (FCN) for semantic segmentation requires a large number of masks with pixel level labelling, which involves a large amount of human labour and time for annotation. In contrast, web images and their…

Contrastive learning has achieved remarkable success in learning effective representations, with supervised contrastive learning often outperforming self-supervised approaches. However, in real-world scenarios, data annotations are often…

The abundance of user-generated data in social media has incentivized the development of methods to infer the latent attributes of users, which are crucially useful for personalization, advertising and recommendation. However, the current…

We consider the problem of retrieving objects from image data and learning to classify them into meaningful semantic categories with minimal supervision. To that end, we propose a fully differentiable unsupervised deep clustering approach…