Related papers: Addressing Discrepancies in Semantic and Visual Al…
We present a novel technique for learning semantic representations, which extends the distributional hypothesis to multilingual data and joint-space embeddings. Our models leverage parallel data and learn to strongly align the embeddings of…
Word representations are created using analogy context-based statistics and lexical relations on words. Word representations are inputs for the learning models in Natural Language Understanding (NLU) tasks. However, to understand language,…
Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques, two or more randomly selected natural images are mixed together to generate an…
Semantic segmentation using convolutional neural networks (CNN) is a crucial component in image analysis. Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is…
Supervised deep learning relies on the assumption that enough training data is available, which presents a problem for its application to several fields, like medical imaging. On the example of a binary image classification task (breast…
Image data augmentation constitutes a critical methodology in modern computer vision tasks, since it can facilitate towards enhancing the diversity and quality of training datasets; thereby, improving the performance and robustness of…
In contrastive self-supervised learning, the common way to learn discriminative representation is to pull different augmented "views" of the same image closer while pushing all other images further apart, which has been proven to be…
Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications. However, the effective integration of T2I models into…
Instance discrimination learns visual representations by treating different augmented views of the same image as positive pairs. While this encourages invariance to handcrafted transformations, same-image positives can preserve nuisance…
Image retrieval is a crucial research topic in computer vision, with broad application prospects ranging from online product searches to security surveillance systems. In recent years, the accuracy and efficiency of image retrieval have…
Recent work has shown that deep vision models tend to be overly dependent on low-level or "texture" features, leading to poor generalization. Various data augmentation strategies have been proposed to overcome this so-called texture bias in…
Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project the visual features to mimic the distribution of textual…
The automatic detection of hypernymy relationships represents a challenging problem in NLP. The successful application of state-of-the-art supervised approaches using distributed representations has generally been impeded by the limited…
Despite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain specific knowledge. This challenge is magnified in natural language processing where no general rules exist for…
The vocabulary mismatch problem is a long-standing problem in information retrieval. Semantic matching holds the promise of solving the problem. Recent advances in language technology have given rise to unsupervised neural models for…
We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and…
Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing…
Mixup is a well-established data augmentation technique, which can extend the training distribution and regularize the neural networks by creating ''mixed'' samples based on the label-equivariance assumption, i.e., a proportional mixup of…
Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, are low-level, data-independent and…
Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be…