Related papers: SSMix: Saliency-Based Span Mixup for Text Classifi…

We introduce Synthetic Bootstrapped Pretraining (SBP), a language model (LM) pretraining procedure that first learns a model of relations between documents from the pretraining dataset and then leverages it to synthesize a vast new corpus…

Next token prediction has been the standard training objective used in large language model pretraining. Representations are learned as a result of optimizing for token-level perplexity. We propose Continuous Concept Mixing (CoCoMix), a…

How to boost speech pre-training with textual data is an unsolved problem due to the fact that speech and text are very different modalities with distinct characteristics. In this paper, we propose a cross-modal Speech and Language Model…

Unsupervised text embedding has shown great power in a wide range of NLP tasks. While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document…

Modern deep networks can be better generalized when trained with noisy samples and regularization techniques. Mixup and CutMix have been proven to be effective for data augmentation to help avoid overfitting. Previous Mixup-based methods…

In many cases of machine learning, research suggests that the development of training data might have a higher relevance than the choice and modelling of classifiers themselves. Thus, data augmentation methods have been developed to improve…

In this paper, we study the problem of image-text matching. Inferring the latent semantic alignment between objects or other salient stuff (e.g. snow, sky, lawn) and the corresponding words in sentences allows to capture fine-grained…

Mixup-based augmentation has been found to be effective for generalizing models during training, especially for Vision Transformers (ViTs) since they can easily overfit. However, previous mixup-based methods have an underlying prior…

To bridge the semantic gap between vision and language (VL), it is necessary to develop a good alignment strategy, which includes handling semantic diversity, abstract representation of visual information, and generalization ability of…

Image retargeting is the task of making images capable of being displayed on screens with different sizes. This work should be done so that high-level visual information and low-level features such as texture remain as intact as possible to…

Existing weakly supervised semantic segmentation (WSSS) methods usually utilize the results of pre-trained saliency detection (SD) models without explicitly modeling the connections between the two tasks, which is not the most efficient…

Continual learning has become increasingly important as it enables NLP models to constantly learn and gain knowledge over time. Previous continual learning methods are mainly designed to preserve knowledge from previous tasks, without much…

Text classification is a crucial and fundamental task in web content mining. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach…

Recent works have shown that Multimodal Large Language Models (MLLMs) are highly vulnerable to hidden-pattern visual illusions, where the hidden content is imperceptible to models but obvious to humans. This deficiency highlights a…

Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using annotated datasets like NLI. Yet, the reliance on manual labels limits scalability. Recent studies leverage large…

The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language…

Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…

We present a framework for learning cross-modal video representations by directly pre-training on raw data to facilitate various downstream video-text tasks. Our main contributions lie in the pre-training framework and proxy tasks. First,…

Accurately describing images with text is a foundation of explainable AI. Vision-Language Models (VLMs) like CLIP have recently addressed this by aligning images and texts in a shared embedding space, expressing semantic similarities…

This paper presents an approach for top-down saliency detection guided by visual classification tasks. We first learn how to compute visual saliency when a specific visual task has to be accomplished, as opposed to most state-of-the-art…