Related papers: Addressing Discrepancies in Semantic and Visual Al…

Data augmentation is a necessity to enhance data efficiency in deep learning. For vision-language pre-training, data is only augmented either for images or for text in previous works. In this paper, we present MixGen: a joint data…

To deal with the exhausting annotations, self-supervised representation learning from unlabeled point clouds has drawn much attention, especially centered on augmentation-based contrastive methods. However, specific augmentations hardly…

In this paper, we present a new approach to the semantic enrichment of mathematical expression problem. Our approach is a combination of statistical machine translation and disambiguation which makes use of surrounding text of the…

We consider the problem of naming objects in complex, natural scenes containing widely varying object appearance and subtly different names. Informed by cognitive research, we propose an approach based on sharing context based object…

Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generating synthetic training…

Data augmentation uses artificially-created examples to support supervised machine learning, adding robustness to the resulting models and helping to account for limited availability of labelled data. We apply and evaluate a synthetic data…

What representation do deep neural networks learn? How similar are images to each other for neural networks? Despite the overwhelming success of deep learning methods key questions about their internal workings still remain largely…

Data augmentation is a key element of deep learning pipelines, as it informs the network during training about transformations of the input data that keep the label unchanged. Manually finding adequate augmentation methods and parameters…

Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization…

Nowadays, due to advanced digital imaging technologies and internet accessibility to the public, the number of generated digital images has increased dramatically. Thus, the need for automatic image enhancement techniques is quite apparent.…

Machine learning driven object detection and classification within non-visible imagery has an important role in many fields such as night vision, all-weather surveillance and aviation security. However, such applications often suffer due to…

Data augmentation policies drastically improve the performance of image recognition tasks, especially when the policies are optimized for the target data and tasks. In this paper, we propose to optimize image recognition models and data…

Subgraph representation learning based on Graph Neural Network (GNN) has exhibited broad applications in scientific advancements, such as predictions of molecular structure-property relationships and collective cellular function. In…

Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence, garnering significant interest from both academic and industrial spheres. However, the training of…

Most, if not all, modern deep learning systems restrict themselves to a single dataset for neural network training and inference. In this article, we are interested in systematic ways to join datasets that are made of similar purposes.…

This paper introduces a simple and effective form of data augmentation for recommender systems. A paraphrase similarity model is applied to widely available textual data, such as reviews and product descriptions, yielding new semantic…

Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation. Reliability encompasses robustness, predictive uncertainty and reduced bias. To improve reliability, we introduce…

In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts. It hypothesizes that for objects with similar appearance, they share similar representation. Our method establishes dependencies…

In this paper, we propose a novel implicit semantic data augmentation (ISDA) approach to complement traditional augmentation techniques like flipping, translation or rotation. Our work is motivated by the intriguing property that deep…

To train a well performing neural network for semantic segmentation, it is crucial to have a large dataset with available ground truth for the network to generalize on unseen data. In this paper we present novel point cloud augmentation…