Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
- URL: http://arxiv.org/abs/2310.05737v3
- Date: Fri, 29 Mar 2024 17:44:41 GMT
- Title: Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
- Authors: Lijun Yu, José Lezama, Nitesh B. Gundavarapu, Luca Versari, Kihyuk Sohn, David Minnen, Yong Cheng, Vighnesh Birodkar, Agrim Gupta, Xiuye Gu, Alexander G. Hauptmann, Boqing Gong, Ming-Hsuan Yang, Irfan Essa, David A. Ross, Lu Jiang,
- Abstract summary: Large Language Models (LLMs) are the dominant models for generative tasks in language.
We introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images.
- Score: 122.63617171522316
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this paper, we introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images using a common token vocabulary. Equipped with this new tokenizer, we show that LLMs outperform diffusion models on standard image and video generation benchmarks including ImageNet and Kinetics. In addition, we demonstrate that our tokenizer surpasses the previously top-performing video tokenizer on two more tasks: (1) video compression comparable to the next-generation video codec (VCC) according to human evaluations, and (2) learning effective representations for action recognition tasks.
Related papers
- Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation [54.21476271127356]
Divot is a Diffusion-Powered Video Tokenizer.
We present Divot-unaVic through video-to-text autoregression and text-to-video generation.
arXiv Detail & Related papers (2024-12-05T18:53:04Z) - Mimir: Improving Video Diffusion Models for Precise Text Understanding [53.72393225042688]
Text serves as the key control signal in video generation due to its narrative nature.
The recent success of large language models (LLMs) showcases the power of decoder-only transformers.
This work addresses this challenge with Mimir, an end-to-end training framework featuring a carefully tailored token fuser.
arXiv Detail & Related papers (2024-12-04T07:26:44Z) - FLIER: Few-shot Language Image Models Embedded with Latent Representations [2.443383032451177]
Few-shot Language Image model embedded with latent representations (FLIER) for image recognition.
We first generate images and corresponding latent representations via Stable Diffusion with the textual inputs from GPT-3.
With latent representations as "models-understandable pixels", we introduce a flexible convolutional neural network with two convolutional layers to be the latent encoder.
arXiv Detail & Related papers (2024-10-10T06:27:46Z) - Beyond Text: Frozen Large Language Models in Visual Signal Comprehension [34.398976855955404]
Vision-to-Language Tokenizer, abbreviated as V2T Tokenizer, transforms an image into a foreign language'' with the combined aid of an encoder-decoder, the LLM vocabulary, and a CLIP model.
We undertake rigorous experiments to validate our method, encompassing understanding tasks like image recognition, image captioning, and visual question answering, as well as image denoising tasks like inpainting, outpainting, deblurring, and shift restoration.
arXiv Detail & Related papers (2024-03-12T17:59:51Z) - Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
Video pre-training is challenging due to the modeling of its dynamics video.
In this paper, we address such limitations in video pre-training with an efficient video decomposition.
Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
arXiv Detail & Related papers (2024-02-05T16:30:49Z) - E-ViLM: Efficient Video-Language Model via Masked Video Modeling with
Semantic Vector-Quantized Tokenizer [5.7254320553764]
E-ViLM is able to learn expressive representations from Video-Language corpus and generalize well to extensive Video-Language tasks.
Our model reaches $39.3$% Top-$1$ accuracy on the MSRVTT benchmark, retaining $91.4$% of the accuracy of state-of-the-art larger VL architecture.
arXiv Detail & Related papers (2023-11-28T22:57:17Z) - Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization [52.935150075484074]
We introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language.
The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image.
This unification empowers LaVIT to serve as an impressive generalist interface to understand and generate multi-modal content simultaneously.
arXiv Detail & Related papers (2023-09-09T03:01:38Z) - OmniVL:One Foundation Model for Image-Language and Video-Language Tasks [117.57580168859512]
We present OmniVL, a new foundation model to support both image-language and video-language tasks using one universal architecture.
We demonstrate, for the first time, such a paradigm benefits both image and video tasks, as opposed to the conventional one-directional transfer.
We introduce a novel unified vision-language contrastive (UniVLC) loss to leverage image-text, video-text, image-label (e.g., image classification), video-label (e.g., video action recognition) data together.
arXiv Detail & Related papers (2022-09-15T17:59:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.