paper-with-me

Zero-Shot Semantic Segmentation

4개 벤치마크 · 논문 67편 · 이 태스크의 논문 보기 →

Benchmarks

COCO-Stuff

결과 15개

MESS

결과 13개

PASCAL VOC

결과 13개

ADE20K-847

결과 1개

Most implemented

Zero-Shot Semantic Segmentation

2019-06-03 · 구현 2개

Papers

Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection

2026-07-08 · Zihao Zhang, Aming Wu, Yang Li, Yahong Han arxiv

In this paper, we study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains. Existing methods mainly rely on simulation…

Zero-Shot Semantic SegmentationDomain GeneralizationData AugmentationObject Detection

LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation

2025-10-29 · Yang Miao, Jan-Nico Zaech, Xi Wang, Fabien Despinoy 외 arxiv

We propose LangHOPS, the first Multimodal Large Language Model (MLLM) based framework for open-vocabulary object-part instance segmentation. Given an image, LangHOPS can jointly detect and segment hierarchical object and…

Zero-Shot Semantic SegmentationInstance Segmentation

Semantic4Safety: Causal Insights from Zero-shot Street View Imagery Segmentation for Urban Road Safety

2025-10-17 · Huan Chen, Ting Han, Siyu Chen, Zhihao Guo 외 arxiv

Street-view imagery (SVI) offers a fine-grained lens on traffic risk, yet two fundamental challenges persist: (1) how to construct street-level indicators that capture accident-related features, and (2) how to quantify t…

Zero-Shot Semantic SegmentationCausal Inference

Solar PV Installation Potential Assessment on Building Facades Based on Vision and Language Foundation Models

2025-10-01 · Ruyu Liu, Dongxu Zhuang, Jianhua Zhang, Arega Getaneh Abate 외 arxiv

Building facades represent a significant untapped resource for solar energy generation in dense urban environments, yet assessing their photovoltaic (PV) potential remains challenging due to complex geometries and semant…

Zero-Shot Semantic SegmentationSpatial Reasoning

Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic Calibration

2025-09-10 · Hyeonseok Kim, Byeongkeun Kang, Yeejin Lee arxiv

Generalized zero-shot semantic segmentation of 3D point clouds aims to classify each point into both seen and unseen classes. A significant challenge with these models is their tendency to make biased predictions, often …

Zero-Shot Semantic SegmentationGeneralized Zero-Shot LearningPoint Cloud SegmentationPoint Clouds

OmniMap: A General Mapping Framework Integrating Optics, Geometry, and Semantics

2025-09-09 · Yinan Deng, Yufeng Yue, Jianyu Dou, Jingyu Zhao 외 arxiv

Robotic systems demand accurate and comprehensive 3D environment perception, requiring simultaneous capture of photo-realistic appearance (optical), precise layout shape (geometric), and open-vocabulary scene understandi…

Zero-Shot Semantic SegmentationScene Understanding

전체 67편 보기 →