相关论文: t-gems: text-guided exit modules for decreasing cl…

Large-scale datasets have been pivotal to the advancements of deep learning models in recent years, but training on such large datasets invariably incurs substantial storage and computational overhead. Meanwhile, real-world datasets often…

Despite their success, unsupervised domain adaptation methods for semantic segmentation primarily focus on adaptation between image domains and do not utilize other abundant visual modalities like depth, infrared and event. This limitation…

Multi-modal approaches employ data from multiple input streams such as textual and visual domains. Deep neural networks have been successfully employed for these approaches. In this paper, we present a novel multi-modal approach that fuses…

In multimodal graph learning, graph structures that integrate information from multiple sources, such as vision and text, can more comprehensively model complex entity relationships. However, the continuous growth of their data scale poses…

Existing text-driven infrared and visible image fusion approaches often rely on textual information at the sentence level, which can lead to semantic noise from redundant text and fail to fully exploit the deeper semantic value of textual…

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained…

Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VLMs focus on either the language or visual branches,…

Image clustering is a crucial but challenging task in multimedia machine learning. Recently the combination of clustering with deep learning has achieved promising performance against conventional methods on high-dimensional image data.…

Multimodal fusion breaks through the boundaries between diverse modalities and has already achieved notable performances. However, in many specialized fields, it is struggling to obtain sufficient alignment data for training, which…

Vision-Language Models (VLMs) exhibit a characteristic "cone effect" in which nonlinear encoders map embeddings into highly concentrated regions of the representation space, contributing to cross-modal separation known as the modality gap.…

Transformer-based pretrained language models (LMs) are ubiquitous across natural language understanding, but cannot be applied to long sequences such as stories, scientific articles and long documents, due to their quadratic complexity.…

Multi-modal Large Language Models (MLLMs) have made significant strides in expanding the capabilities of Large Language Models (LLMs) through the incorporation of visual perception interfaces. Despite the emergence of exciting applications…

We introduce T5Gemma 2, the next generation of the T5Gemma family of lightweight open encoder-decoder models, featuring strong multilingual, multimodal and long-context capabilities. T5Gemma 2 follows the adaptation recipe (via UL2) in…

Increasing AI computing demands and slowing transistor scaling have led to the advent of Multi-Chip-Module (MCMs) based accelerators. MCMs enable cost-effective scalability, higher yield, and modular reuse by partitioning large chips into…

Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia…

In this work, we present a conceptually simple and effective method to train a strong bilingual/multilingual multimodal representation model. Starting from the pre-trained multimodal representation model CLIP released by OpenAI, we altered…

Recent advances in multimodal large language models (MLLMs) have enabled image-based question-answering capabilities. However, a key limitation is the use of CLIP as the visual encoder; while it can capture coarse global information, it…

Standard decoding approaches rely on model-based channel estimation methods to compensate for varying channel effects, which degrade in performance whenever there is a model mismatch. Recently proposed Deep learning based neural decoders…

Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP). However, computational complexity and rate flexibility are still two major challenges for its practical…

Autoencoders have been widely used for dimensional reduction and feature extraction. Various types of autoencoders have been proposed by introducing regularization terms. Most of these regularizations improve representation learning by…