Related papers: Contrastive Mutual Information Learning: Toward Ro…

Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks than joint-training methods relying on task-specific supervision. In this paper, we found…

Recent work has compared neural network representations via similarity-based analyses to improve model interpretation. The quality of a similarity measure is typically evaluated by its success in assigning a high score to representations…

Multimodal Contrastive Learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space. By leveraging contrastive learning across diverse modalities, large-scale multimodal data enhances…

Detecting anomalies is one fundamental aspect of a safety-critical software system, however, it remains a long-standing problem. Numerous branches of works have been proposed to alleviate the complication and have demonstrated their…

This paper proposes a method for representation learning of multimodal data using contrastive losses. A traditional approach is to contrast different modalities to learn the information shared between them. However, that approach could fail…

Recent research has devoted considerable effort to verifying the intermediate reasoning steps of chain-of-thought (CoT) trajectories using process reward models (PRMs) and other verifier models. However, training a PRM typically requires…

This paper proposes a cold start recommendation model that integrates contrastive learning, aiming to solve the problem of performance degradation of recommendation systems in cold start scenarios due to the scarcity of user and item…

Mutual Information (MI) plays an important role in representation learning. However, MI is unfortunately intractable in continuous and high-dimensional settings. Recent advances establish tractable and scalable MI estimators to discover…

In Masked Image Modeling (MIM), two primary methods exist: Pixel MIM and Latent MIM, each utilizing different reconstruction targets, raw pixels and latent representations, respectively. Pixel MIM tends to capture low-level visual details…

Monaural speech enhancement (SE) is an ill-posed problem due to the irreversible degradation process. Recent methods to achieve SE tasks rely solely on positive information, e.g., ground-truth speech and speech-relevant features. Different…

Human activity recognition serves as the foundation for various emerging applications. In recent years, researchers have used collaborative sensing of multi-source sensors to capture complex and dynamic human activities. However, multimodal…

Real-life medical data is often multimodal and incomplete, fueling the growing need for advanced deep learning models capable of integrating them efficiently. The use of diverse modalities, including histopathology slides, MRI, and genetic…

Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…

We address the task of controlled generation of small molecules, which entails finding novel molecules with desired properties under certain constraints (e.g., similarity to a reference molecule). Here we introduce MolMIM, a probabilistic…

Masked Image Modeling (MIM) offers a promising approach to self-supervised representation learning, however existing MIM models still lag behind the state-of-the-art. In this paper, we systematically analyze target representations, loss…

Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that are tokenized from images or generated by pre-trained models…

Modeling holistic user interests is important for improving recommendation systems but is challenged by high computational cost and difficulty in handling diverse information with full behavior context. Existing search-based methods might…

Incomplete Multi-View Clustering aims to enhance clustering performance by using data from multiple modalities. Despite the fact that several approaches for studying this issue have been proposed, the following drawbacks still persist: 1)…

Detecting Mild Cognitive Impairment from picture descriptions is critical yet challenging, especially in multilingual and multiple picture settings. Prior work has primarily focused on English speakers describing a single picture (e.g., the…

The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual representations can be done by masking input image parts while…