QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation

• URL: http://arxiv.org/abs/2502.05178v1
• Date: Fri, 07 Feb 2025 18:59:57 GMT
• Title: QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
• Authors: Yue Zhao, Fuzhao Xue, Scott Reed, Linxi Fan, Yuke Zhu, Jan Kautz, Zhiding Yu, Philipp Krähenbühl, De-An Huang,
• Abstract summary: Quantized Language-Image Pretraining (QLIP) combines state-of-the-art reconstruction quality with state-of-the-art zero-shot image understanding. QLIP trains a binary-spherical-quantization-based autoencoder with reconstruction and language-image alignment objectives. We demonstrate that QLIP enables a unified mixed-modality auto-regressive model for understanding and generation.
• Score: 101.28446308930367
• License:
• Abstract: We introduce Quantized Language-Image Pretraining (QLIP), a visual tokenization method that combines state-of-the-art reconstruction quality with state-of-the-art zero-shot image understanding. QLIP trains a binary-spherical-quantization-based autoencoder with reconstruction and language-image alignment objectives. We are the first to show that the two objectives do not need to be at odds. We balance the two loss terms dynamically during training and show that a two-stage training pipeline effectively mixes the large-batch requirements of image-language pre-training with the memory bottleneck imposed by the reconstruction objective. We validate the effectiveness of QLIP for multimodal understanding and text-conditioned image generation with a single model. Specifically, QLIP serves as a drop-in replacement for the visual encoder for LLaVA and the image tokenizer for LlamaGen with comparable or even better performance. Finally, we demonstrate that QLIP enables a unified mixed-modality auto-regressive model for understanding and generation.

Related papers

• VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model [38.61292051733335]
  We present VARGPT, a novel multimodal large language model (MLLM) that unifies visual understanding and generation within a single autoregressive framework. VarGPT employs a next-token prediction paradigm for visual understanding and a next-scale prediction paradigm for visual autoregressive generation. Notably, VARGPT naturally supports capabilities in autoregressive visual generation and instruction-to-image synthesis, showcasing its versatility in both visual understanding and generation tasks.
  arXiv  Detail & Related papers  (2025-01-21T17:50:43Z)
• VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation [79.02357561313785]
  We introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for both image and text modalities by employing a straightforward auto-regressive objective.
  arXiv  Detail & Related papers  (2023-12-14T18:59:43Z)
• Synchronizing Vision and Language: Bidirectional Token-Masking AutoEncoder for Referring Image Segmentation [26.262887028563163]
  Referring Image (RIS) aims to segment target objects expressed in natural language within a scene at the pixel level. We propose a novel bidirectional token-masking autoencoder (BTMAE) inspired by the masked autoencoder (MAE) BTMAE learns the context of image-to-language and language-to-image by reconstructing missing features in both image and language features at the token level.
  arXiv  Detail & Related papers  (2023-11-29T07:33:38Z)
• Controlling Vision-Language Models for Multi-Task Image Restoration [6.239038964461397]
  We present a degradation-aware vision-language model (DA-CLIP) to better transfer pretrained vision-language models to low-level vision tasks. Our approach advances state-of-the-art performance on both emphdegradation-specific and emphunified image restoration tasks.
  arXiv  Detail & Related papers  (2023-10-02T09:10:16Z)
• Planting a SEED of Vision in Large Language Model [73.17530130368053]
  We present SEED, an elaborate image tokenizer that empowers Large Language Models (LLMs) with the ability to SEE and Draw at the same time. This version of SEED was trained in 5.7 days using only 64 V100 GPUs and 5M publicly available image-text pairs.
  arXiv  Detail & Related papers  (2023-07-16T13:41:39Z)
• Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation [78.13793505707952]
  Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook. We propose a novel two-stage framework, which consists of Masked Quantization VAE (MQ-VAE) Stack model from modeling redundancy.
  arXiv  Detail & Related papers  (2023-05-23T02:15:53Z)
• DU-VLG: Unifying Vision-and-Language Generation via Dual Sequence-to-Sequence Pre-training [37.15272352614968]
  We propose DU-VLG, a framework which unifies vision-and-language generation as sequence generation problems. Du-VLG is trained with novel dual pre-training tasks: multi-modal denoising autoencoder tasks and modality translation tasks. Results show that DU-VLG yields better performance than variants trained with uni-directional generation objectives or the variant without the commitment loss.
  arXiv  Detail & Related papers  (2022-03-17T03:18:22Z)
• UFO: A UniFied TransfOrmer for Vision-Language Representation Learning [54.82482779792115]
  We propose a single UniFied transfOrmer (UFO) capable of processing either unimodal inputs (e.g., image or language) or multimodal inputs (e.g., the concatenation of the image and the question) for vision-language (VL) representation learning. Existing approaches typically design an individual network for each modality and/or a specific fusion network for multimodal tasks.
  arXiv  Detail & Related papers  (2021-11-19T03:23:10Z)
• StEP: Style-based Encoder Pre-training for Multi-modal Image Synthesis [68.3787368024951]
  We propose a novel approach for multi-modal Image-to-image (I2I) translation. We learn a latent embedding, jointly with the generator, that models the variability of the output domain. Specifically, we pre-train a generic style encoder using a novel proxy task to learn an embedding of images, from arbitrary domains, into a low-dimensional style latent space.
  arXiv  Detail & Related papers  (2021-04-14T19:58:24Z)

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.