paper-with-me

홈 › Papers

Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks

2024-01-25 · Tianhe Ren, Shilong Liu, Ailing Zeng, Jing Lin, Kunchang Li, He Cao, Jiayu Chen, Xinyu Huang, Yukang Chen, Feng Yan, Zhaoyang Zeng, Hao Zhang, Feng Li, Jie Yang, Hongyang Li, Qing Jiang, Lei Zhang

We introduce Grounded SAM, which uses Grounding DINO as an open-set object detector to combine with the segment anything model (SAM). This integration enables the detection and segmentation of any regions based on arbitrary text inputs and opens a door to connecting various vision models. As shown in Fig.1, a wide range of vision tasks can be achieved by using the versatile Grounded SAM pipeline. For example, an automatic annotation pipeline based solely on input images can be realized by incorporating models such as BLIP and Recognize Anything. Additionally, incorporating Stable-Diffusion allows for controllable image editing, while the integration of OSX facilitates promptable 3D human motion analysis. Grounded SAM also shows superior performance on open-vocabulary benchmarks, achieving 48.7 mean AP on SegInW (Segmentation in the wild) zero-shot benchmark with the combination of Grounding DINO-Base and SAM-Huge models.

📄 PDF Abstract BibTeX arXiv:2401.14159

Code (5)

IDEA-Research/Grounded-Segment-Anything 공식 구현 pytorch
haiv-lab/ospcoop_imagenet-bg pytorch
idea-research/grounded-sam-2 pytorch
idea-research/groundingdino pytorch
syscv/sam-hq pytorch

Tasks

Segmentation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

A2P-Vis: an Analyzer-to-Presenter Agentic Pipeline for Visual Insights Generation and Reporting

2025-12-26 · Shuyu Gan, Renxiang Wang, James Mooney, Dongyeop Kang arxiv

Automating end-to-end data science pipeline with AI agents still stalls on two gaps: generating insightful, diverse visual evidence and assembling it into a coherent, professional report. We present A2P-Vis, a two-part, …

Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI

2025-11-25 · Xinhao Liu, Jiaqi Li, Youming Deng, Ruxin Chen 외 arxiv

Reproducible closed-loop evaluation remains a major bottleneck in Embodied AI such as visual navigation. A promising path forward is high-fidelity simulation that combines photorealistic sensor rendering with geometrical…

Novel View Synthesis3D ReconstructionVisual Navigation

Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs

2022-12-01 · CVPR 2023 1 · Junbum Cha, Jonghwan Mun, Byungseok Roh

We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have s…

Contrastive LearningOpen Vocabulary Semantic SegmentationSegmentationSemantic Segmentation+2

Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks

2022-03-25 · Jiacong Hu, Jing Gao, Jingwen Ye, Yang Gao 외

With the rapid development of deep learning, the increasing complexity and scale of parameters make training a new model increasingly resource-intensive. In this paper, we start from the classic convolutional neural netw…

Incremental LearningKnowledge DistillationModel CompressionTransfer Learning

World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models

2023-06-14 · Ziqiao Ma, Jiayi Pan, Joyce Chai

The ability to connect language units to their referents in the physical world, referred to as grounding, is crucial to learning and understanding grounded meanings of words. While humans demonstrate fast mapping in new …

Grounded Open Vocabulary AcquisitionLanguage ModelingLanguage Modelling