Towards More Unified In-context Visual Understanding
- URL: http://arxiv.org/abs/2312.02520v2
- Date: Sat, 16 Mar 2024 16:07:33 GMT
- Title: Towards More Unified In-context Visual Understanding
- Authors: Dianmo Sheng, Dongdong Chen, Zhentao Tan, Qiankun Liu, Qi Chu, Jianmin Bao, Tao Gong, Bin Liu, Shengwei Xu, Nenghai Yu,
- Abstract summary: We present a new ICL framework for visual understanding with multi-modal output enabled.
First, we quantize and embed both text and visual prompt into a unified representational space.
Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them.
- Score: 74.55332581979292
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such as semantic segmentation and image captioning, yielding promising results. However, existing visual ICL framework can not enable producing content across multiple modalities, which limits their potential usage scenarios. To address this issue, we present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space, structured as interleaved in-context sequences. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them, facilitating in-context learning. Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline.Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines. Overall, our research takes a further step toward unified multimodal in-context learning.
Related papers
- X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs [49.30255148577368]
X-Former is a lightweight transformer module designed to exploit the complementary strengths of CL and MIM.
X-Former first bootstraps vision-language representation learning and multimodal-to-multimodal generative learning from two frozen vision encoders.
It further bootstraps vision-to-language generative learning from a frozen LLM to ensure visual features from X-Former can be interpreted by the LLM.
arXiv Detail & Related papers (2024-07-18T18:39:54Z) - Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets.
However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs.
This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
arXiv Detail & Related papers (2024-07-05T17:43:30Z) - Explaining Multi-modal Large Language Models by Analyzing their Vision Perception [4.597864989500202]
This research proposes a novel approach to enhance the interpretability of MLLMs by focusing on the image embedding component.
We combine an open-world localization model with a MLLM, thus creating a new architecture able to simultaneously produce text and object localization outputs from the same vision embedding.
arXiv Detail & Related papers (2024-05-23T14:24:23Z) - Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception [63.03288425612792]
We propose bfAnyRef, a general MLLM model that can generate pixel-wise object perceptions and natural language descriptions from multi-modality references.
Our model achieves state-of-the-art results across multiple benchmarks, including diverse modality referring segmentation and region-level referring expression generation.
arXiv Detail & Related papers (2024-03-05T13:45:46Z) - Concept-Guided Prompt Learning for Generalization in Vision-Language
Models [33.361744437967126]
We propose Concept-Guided Prompt Learning for vision-language models.
We leverage the well-learned knowledge of Contrastive Language-Image Pretraining to create a visual concept cache.
In order to refine the text features, we develop a projector that transforms multi-level visual features into text features.
arXiv Detail & Related papers (2024-01-15T04:04:47Z) - Improving In-Context Learning in Diffusion Models with Visual
Context-Modulated Prompts [83.03471704115786]
We introduce improved Prompt Diffusion (iPromptDiff) in this study.
iPromptDiff integrates an end-to-end trained vision encoder that converts visual context into an embedding vector.
We show that a diffusion-based vision foundation model, when equipped with this visual context-modulated text guidance and a standard ControlNet structure, exhibits versatility and robustness across a variety of training tasks.
arXiv Detail & Related papers (2023-12-03T14:15:52Z) - Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal
Structured Representations [70.41385310930846]
We present an end-to-end framework Structure-CLIP to enhance multi-modal structured representations.
We use scene graphs to guide the construction of semantic negative examples, which results in an increased emphasis on learning structured representations.
A Knowledge-Enhance (KEE) is proposed to leverage SGK as input to further enhance structured representations.
arXiv Detail & Related papers (2023-05-06T03:57:05Z) - Contrastive Language-Image Pre-Training with Knowledge Graphs [33.211811772961234]
We propose a knowledge-based pre-training framework, dubbed Knowledge-CLIP, which injects semantic information into the widely used CLIP model.
Our model can semantically align the representations in vision and language with higher quality, and enhance the reasoning ability across scenarios and modalities.
arXiv Detail & Related papers (2022-10-17T09:49:22Z)
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.