Related papers: Alignment Unlocks Complementarity: A Framework for…

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input…

Learning multilingual representations of text has proven a successful method for many cross-lingual transfer learning tasks. There are two main paradigms for learning such representations: (1) alignment, which maps different independently…

Multi-modal fusion methods often suffer from two types of representation collapse: feature collapse where individual dimensions lose their discriminative power (as measured by eigenspectra), and modality collapse where one dominant modality…

Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-based pretraining task. However, their performance is often…

Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work,…

Multiview learning has drawn widespread attention for its efficacy in leveraging cross-view consensus and complementarity information to achieve a comprehensive representation of data. While multi-view learning has undergone vigorous…

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures…

Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal…

Multi-modal representation learning has become a pivotal area in artificial intelligence, enabling the integration of diverse modalities such as vision, text, and audio to solve complex problems. However, existing approaches predominantly…

This paper presents a novel approach towards creating a foundational model for aligning neural data and visual stimuli across multimodal representationsof brain activity by leveraging contrastive learning. We used electroencephalography…

Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail…

Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the…

Multimodal representation learning has shown promising improvements on various vision-language tasks. Most existing methods excel at building global-level alignment between vision and language while lacking effective fine-grained image-text…

Multimodal remote sensing semantic segmentation enhances scene interpretation by exploiting complementary physical cues from heterogeneous data. Although pretrained Vision Foundation Models (VFMs) provide strong general-purpose…

We introduce LayerLock, a simple yet effective approach for self-supervised visual representation learning, that gradually transitions from pixel to latent prediction through progressive layer freezing. First, we make the observation that…

Multi-view subspace clustering aims to divide a set of multisource data into several groups according to their underlying subspace structure. Although the spectral clustering based methods achieve promotion in multi-view clustering, their…

Consistency and complementarity are two key ingredients for boosting multi-view clustering (MVC). Recently with the introduction of popular contrastive learning, the consistency learning of views has been further enhanced in MVC, leading to…

Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal…

Masked image modelling (e.g., Masked AutoEncoder) and contrastive learning (e.g., Momentum Contrast) have shown impressive performance on unsupervised visual representation learning. This work presents Masked Contrastive Representation…

Self-supervised learning is popular method because of its ability to learn features in images without using its labels and is able to overcome limited labeled datasets used in supervised learning. Self-supervised learning works by using a…