paper-with-me

홈 › Papers

Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos

2023-12-07 · CVPR 2024 1 · Mehmet Saygin Seyfioglu, Wisdom O. Ikezogwo, Fatemeh Ghezloo, Ranjay Krishna, Linda Shapiro

Diagnosis in histopathology requires a global whole slide images (WSIs) analysis, requiring pathologists to compound evidence from different WSI patches. The gigapixel scale of WSIs poses a challenge for histopathology multi-modal models. Training multi-model models for histopathology requires instruction tuning datasets, which currently contain information for individual image patches, without a spatial grounding of the concepts within each patch and without a wider view of the WSI. Therefore, they lack sufficient diagnostic capacity for histopathology. To bridge this gap, we introduce Quilt-Instruct, a large-scale dataset of 107,131 histopathology-specific instruction question/answer pairs, grounded within diagnostically relevant image patches that make up the WSI. Our dataset is collected by leveraging educational histopathology videos from YouTube, which provides spatial localization of narrations by automatically extracting the narrators' cursor positions. Quilt-Instruct supports contextual reasoning by extracting diagnosis and supporting facts from the entire WSI. Using Quilt-Instruct, we train Quilt-LLaVA, which can reason beyond the given single image patch, enabling diagnostic reasoning across patches. To evaluate Quilt-LLaVA, we propose a comprehensive evaluation dataset created from 985 images and 1283 human-generated question-answers. We also thoroughly evaluate Quilt-LLaVA using public histopathology datasets, where Quilt-LLaVA significantly outperforms SOTA by over 10% on relative GPT-4 score and 4% and 9% on open and closed set VQA. Our code, data, and model are publicly accessible at quilt-llava.github.io.

📄 PDF Abstract BibTeX arXiv:2312.04746

Code (2)

aldraus/quilt-llava pytorch
wisdomikezogwo/quilt1m pytorch

Tasks

DiagnosticImage CaptioningVisual Question Answering (VQA)whole slide images

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
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…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Visual Instruction Tuning

2023-04-17 · NeurIPS 2023 11 · Haotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae Lee

Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. In this paper, w…

1 Image, 2*2 Stitching3D Question Answering (3D-QA)Image ClassificationImage Retrieval+9

To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning

2023-11-13 · Junke Wang, Lingchen Meng, Zejia Weng, Bo He 외

Existing visual instruction tuning methods typically prompt large language models with textual descriptions to generate instruction-following data. Despite the promising performance achieved, these descriptions are deriv…

Instruction FollowingMM-VetVisual Question Answering

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

2023-06-29 · Yanzhe Zhang, Ruiyi Zhang, Jiuxiang Gu, Yufan Zhou 외

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 imag…

16kImage CaptioningInstruction FollowingOptical Character Recognition (OCR)+1

Generative Visual Instruction Tuning

2024-06-17 · Jefferson Hernandez, Ruben Villegas, Vicente Ordonez

We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by cu…

Image GenerationImage-text matchingInstruction FollowingLanguage Modeling+4

SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant

2024-03-17 · Guohao Sun, Can Qin, Jiamian Wang, Zeyuan Chen 외

Recent advances in vision-language models have shown notable generalization in broad tasks through visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models…

Language ModellingQuestion AnsweringSelf-Supervised LearningVisual Question Answering