Related papers: CoCoSoDa: Effective Contrastive Learning for Code …

Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to train on synthetic data sampled from LLMs. In this work, we…

Recently, the advent of Large Visual-Language Models (LVLMs) has received increasing attention across various domains, particularly in the field of visual document understanding (VDU). Different from conventional vision-language tasks, VDU…

Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized code (such as performant CUDA kernels and competition-level…

Context: Code Clone Detection (CCD) is a software engineering task that is used for plagiarism detection, code search, and code comprehension. Recently, deep learning-based models have achieved an F1 score (a metric used to assess…

Recently, neural networks have shown impressive progress across diverse fields, with speech processing being no exception. However, recent breakthroughs in this area require extensive offline training using large datasets and tremendous…

In addition to relevance, diversity is an important yet less studied performance metric of cross-modal image retrieval systems, which is critical to user experience. Existing solutions for diversity-aware image retrieval either explicitly…

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

Code search is vital in the maintenance and extension of software systems. Past works have used separate language models for the natural language and programming language artifacts on models with multiple encoders and different loss…

MoCo is effective for unsupervised image representation learning. In this paper, we propose VideoMoCo for unsupervised video representation learning. Given a video sequence as an input sample, we improve the temporal feature representations…

Co-Salient Object Detection (CoSOD) aims at simulating the human visual system to discover the common and salient objects from a group of relevant images. Recent methods typically develop sophisticated deep learning based models have…

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of…

While deep learning has contributed to the advancement of sensor-based Human Activity Recognition (HAR), it is usually a costly and challenging supervised task with the needs of a large amount of labeled data. To alleviate this issue,…

Unsupervised learning has recently made exceptional progress because of the development of more effective contrastive learning methods. However, CNNs are prone to depend on low-level features that humans deem non-semantic. This dependency…

Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios. Contrastive pre-training, which constructs pseudo-positive examples from unlabeled data, has shown great…

We show that bringing intermediate layers' representations of two augmented versions of an image closer together in self-supervised learning helps to improve the momentum contrastive (MoCo) method. To this end, in addition to the…

Retrieval-augmented generation has proven practical when models require specialized knowledge or access to the latest data. However, existing methods for multimodal document retrieval often replicate techniques developed for text-only…

Long-tailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples. Such imbalance issue considerably impairs the performance of standard supervised learning…

Weakly supervised object detection (WSOD) aims at learning precise object detectors with only image-level tags. In spite of intensive research on deep learning (DL) approaches over the past few years, there is still a significant…

Following SimCSE, contrastive learning based methods have achieved the state-of-the-art (SOTA) performance in learning sentence embeddings. However, the unsupervised contrastive learning methods still lag far behind the supervised…