paper-with-me

홈 › Papers

LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding

2023-06-29 · Yanzhe Zhang, Ruiyi Zhang, Jiuxiang Gu, Yufan Zhou, Nedim Lipka, Diyi Yang, Tong Sun

Instruction tuning unlocks the superior capability of Large Language Models (LLM) to interact with humans. Furthermore, recent instruction-following datasets include images as visual inputs, collecting responses for image-based instructions. However, visual instruction-tuned models cannot comprehend textual details within images well. This work enhances the current visual instruction tuning pipeline with text-rich images (e.g., movie posters, book covers, etc.). Specifically, we first use publicly available OCR tools to collect results on 422K text-rich images from the LAION dataset. Moreover, we prompt text-only GPT-4 with recognized texts and image captions to generate 16K conversations, each containing question-answer pairs for text-rich images. By combining our collected data with previous multi-modal instruction-following data, our model, LLaVAR, substantially improves the LLaVA model's capability on text-based VQA datasets (up to 20% accuracy improvement) while achieving an accuracy of 91.42% on ScienceQA. The GPT-4-based instruction-following evaluation also demonstrates the improvement of our model on both natural images and text-rich images. Through qualitative analysis, LLaVAR shows promising interaction (e.g., reasoning, writing, and elaboration) skills with humans based on the latest real-world online content that combines text and images. We make our code/data/models publicly available at https://llavar.github.io/.

📄 PDF Abstract BibTeX arXiv:2306.17107

Code (2)

SALT-NLP/LLaVAR 공식 구현 pytorch
llavar/llavar-2 pytorch

Tasks

16kImage CaptioningInstruction FollowingOptical Character Recognition (OCR)Visual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generation

2024-12-20 · Shijie Zhou, Ruiyi Zhang, Yufan Zhou, Changyou Chen

Large multimodal models still struggle with text-rich images because of inadequate training data. Self-Instruct provides an annotation-free way for generating instruction data, but its quality is poor, as multimodal alig…

Image Captioning

Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Models

2023-08-25 · Chi Chen, Ruoyu Qin, Fuwen Luo, Xiaoyue Mi 외

Recently, Multimodal Large Language Models (MLLMs) that enable Large Language Models (LLMs) to interpret images through visual instruction tuning have achieved significant success. However, existing visual instruction tu…

cross-modal alignmentPosition

VILA: On Pre-training for Visual Language Models

2023-12-12 · CVPR 2024 1 · Ji Lin, Hongxu Yin, Wei Ping, Yao Lu 외

Visual language models (VLMs) rapidly progressed with the recent success of large language models. There have been growing efforts on visual instruction tuning to extend the LLM with visual inputs, but lacks an in-depth …

In-Context LearningLanguage ModellingVisual Question AnsweringWorld Knowledge+1

Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction

2024-02-06 · Yonggang Jin, Ge Zhang, Hao Zhao, Tianyu Zheng 외

Developing a generalist agent is a longstanding objective in artificial intelligence. Previous efforts utilizing extensive offline datasets from various tasks demonstrate remarkable performance in multitasking scenarios …

Bridging Writing Manner Gap in Visual Instruction Tuning by Creating LLM-aligned Instructions

2025-03-24 · Dong Jing, Nanyi Fei, Zhiwu Lu

In the realm of Large Multi-modal Models (LMMs), the instruction quality during the visual instruction tuning stage significantly influences the performance of modality alignment. In this paper, we assess the instruction…

Sentence