paper-with-me

Papers

TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation

2024-02-24 · Zekun Jiang, Dongjie Cheng, Ziyuan Qin, Jun Gao, Qicheng Lao, Abdullaev Bakhrom Ismoilovich, Urazboev Gayrat, Yuldashov Elyorbek, Bekchanov Habibullo, Defu Tang, LinJing Wei, Kang Li, Le Zhang

This study presents a novel multimodal medical image zero-shot segmentation algorithm named the text-visual-prompt segment anything model (TV-SAM) without any manual annotations. The TV-SAM incorporates and integrates the large language model GPT-4, the vision language model GLIP, and the SAM to autonomously generate descriptive text prompts and visual bounding box prompts from medical images, thereby enhancing the SAM's capability for zero-shot segmentation. Comprehensive evaluations are implemented on seven public datasets encompassing eight imaging modalities to demonstrate that TV-SAM can effectively segment unseen targets across various modalities without additional training. TV-SAM significantly outperforms SAM AUTO and GSAM, closely matching the performance of SAM BBOX with gold standard bounding box prompts and surpasses the state-of-the-art methods on specific datasets such as ISIC and WBC. The study indicates that TV-SAM serves as an effective multimodal medical image zero-shot segmentation algorithm, highlighting the significant contribution of GPT-4 to zero-shot segmentation. By integrating foundational models such as GPT-4, GLIP, and SAM, the ability to address complex problems in specialized domains can be enhanced.

📄 PDF Abstract BibTeX arXiv:2402.15759

Code (1)

jzk00/tv-sam 공식 구현

Tasks

DescriptiveLanguage ModelingLanguage ModellingLarge Language ModelSegmentationZero Shot Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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…

Similar Papers 제목 키워드 기반

M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning

2024-09-24 · Taowen Wang, Yiyang Liu, James Chenhao Liang, Junhan Zhao 외

Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across variou…

Zero-shot Generalization

2nd Place Winning Solution for the CVPR2023 Visual Anomaly and Novelty Detection Challenge: Multimodal Prompting for Data-centric Anomaly Detection

2023-06-15 · Yunkang Cao, Xiaohao Xu, Chen Sun, Yuqi Cheng 외

This technical report introduces the winning solution of the team Segment Any Anomaly for the CVPR2023 Visual Anomaly and Novelty Detection (VAND) challenge. Going beyond uni-modal prompt, e.g., language prompt, we prese…

Anomaly DetectionAnomaly LocalizationAnomaly SegmentationNovelty Detection+2

OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation

2024-03-21 · Kwanyoung Kim, Yujin Oh, Jong Chul Ye

The recent success of CLIP has demonstrated promising results in zero-shot semantic segmentation by transferring muiltimodal knowledge to pixel-level classification. However, leveraging pre-trained CLIP knowledge to clos…

Semantic SegmentationZero-Shot Semantic Segmentation

Segment Any Mesh: Zero-shot Mesh Part Segmentation via Lifting Segment Anything 2 to 3D

2024-08-24 · George Tang, William Zhao, Logan Ford, David Benhaim 외

We propose Segment Any Mesh (SAMesh), a novel zero-shot method for mesh part segmentation that overcomes the limitations of shape analysis-based, learning-based, and current zero-shot approaches. SAMesh operates in two p…

DiversitySegmentation

Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models

2025-06-06 · Seung-jae Lee, Paul Hongsuck Seo

Audiovisual segmentation (AVS) aims to identify visual regions corresponding to sound sources, playing a vital role in video understanding, surveillance, and human-computer interaction. Traditional AVS methods depend on …

SegmentationVideo Understanding