相关论文: HieraTok: Multi-Scale Visual Tokenizer Improves Im…

Document image enhancement is a fundamental and important stage for attaining the best performance in any document analysis assignment because there are many degradation situations that could harm document images, making it more difficult…

Tokenizer, serving as a translator to map the intricate visual data into a compact latent space, lies at the core of visual generative models. Based on the finding that existing tokenizers are tailored to image or video inputs, this paper…

Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from…

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

Due to its deficiency in prior knowledge (inductive bias), Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. Moreover, the growing layers and parameters in ViT models impede their applicability to…

The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a…

Autoregressive image generation aims to predict the next token based on previous ones. However, this process is challenged by the bidirectional dependencies inherent in conventional image tokenizations, which creates a fundamental…

In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two…

Real-time transmission of visual data over wireless networks remains highly challenging, even when leveraging advanced deep neural networks, particularly under severe channel conditions such as limited bandwidth and weak connectivity. In…

Recent advances in visual generation have emphasized the importance of Latent Generative Models (LGMs), which critically depend on effective visual tokenizers to bridge pixels and semantic representations. However, tokenizers constructed on…

Image tokenization has enabled major advances in autoregressive image generation by providing compressed, discrete representations that are more efficient to process than raw pixels. While traditional approaches use 2D grid tokenization,…

Video-to-Speech (VTS) generation aims to synthesize speech from a silent video without auditory signals. However, existing VTS methods disregard the hierarchical nature of speech, which spans coarse speaker-aware semantics to fine-grained…

The accelerated MRI reconstruction process presents a challenging ill-posed inverse problem due to the extensive under-sampling in k-space. Recently, Vision Transformers (ViTs) have become the mainstream for this task, demonstrating…

Vision Transformer (ViT) models have made breakthroughs in image embedding extraction, which provide state-of-the-art performance in tasks such as zero-shot image classification. However, the models suffer from a high computational burden.…

Unified Multimodal Large Language Models (MLLMs) require a visual representation that simultaneously supports high-fidelity reconstruction, complex semantic extraction, and generative suitability. However, existing visual tokenizers…

Vision Transformers (ViTs) have achieved remarkable success in various computer vision tasks. However, ViTs have a huge computational cost due to their inherent reliance on multi-head self-attention (MHSA), prompting efforts to accelerate…

Vision Transformers (ViTs) have achieved strong performance in visual recognition, yet their deployment in resource-constrained industrial environments remains limited. Some main challenges are their high computational cost, memory…

We attempt to reduce the computational costs in vision transformers (ViTs), which increase quadratically in the token number. We present a novel training paradigm that trains only one ViT model at a time, but is capable of providing…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization, which involves efficiently transforming input visual signals into…

Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large-scale, high-quality private datasets, making them…