paper-with-me

홈 › Papers

SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images

2024-07-12 · Josh Myers-Dean, Jarek Reynolds, Brian Price, Yifei Fan, Danna Gurari

Hierarchical segmentation entails creating segmentations at varying levels of granularity. We introduce the first hierarchical semantic segmentation dataset with subpart annotations for natural images, which we call SPIN (SubPartImageNet). We also introduce two novel evaluation metrics to evaluate how well algorithms capture spatial and semantic relationships across hierarchical levels. We benchmark modern models across three different tasks and analyze their strengths and weaknesses across objects, parts, and subparts. To facilitate community-wide progress, we publicly release our dataset at https://joshmyersdean.github.io/spin/index.html.

📄 PDF Abstract BibTeX arXiv:2407.09686

Code (0)

등록된 구현이 없습니다.

Tasks

SegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Hierarchical Open-vocabulary Universal Image Segmentation

2023-07-03 · NeurIPS 2023 11 · Xudong Wang, Shufan Li, Konstantinos Kallidromitis, Yusuke Kato 외

Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted a…

Image ComprehensionImage Segmentationobject-detectionObject Detection+7

HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network

2022-03-21 · CVPR 2022 1 · Chang Yu, Xiangyu Zhu, Xiaomei Zhang, Zidu Wang 외

Capsule networks are designed to present the objects by a set of parts and their relationships, which provide an insight into the procedure of visual perception. Although recent works have shown the success of capsule ne…

View-Consistent Hierarchical 3D Segmentation Using Ultrametric Feature Fields

2024-05-30 · Haodi He, Colton Stearns, Adam W. Harley, Leonidas J. Guibas

Large-scale vision foundation models such as Segment Anything (SAM) demonstrate impressive performance in zero-shot image segmentation at multiple levels of granularity. However, these zero-shot predictions are rarely 3D…

Image SegmentationNeRFSegmentationSemantic Segmentation

RealVLG-R1: A Large-Scale Real-World Visual-Language Grounding Benchmark for Robotic Perception and Manipulation

2026-03-16 · Linfei Li, Lin Zhang, Ying Shen arxiv

Visual-language grounding aims to establish semantic correspondences between natural language and visual entities, enabling models to accurately identify and localize target objects based on textual instructions. Existin…

Robotic Grasping

LUMOS: Universal Semi-Supervised OCT Retinal Layer Segmentation with Hierarchical Reliable Mutual Learning

2026-04-07 · Yizhou Fang, Jian Zhong, Li Lin, Xiaoying Tang arxiv

Optical Coherence Tomography (OCT) layer segmentation faces challenges due to annotation scarcity and heterogeneous label granularities across datasets. While semi-supervised learning helps alleviate label scarcity, exis…