paper-with-me

Papers Superpixels

“Superpixels” 태그가 달린 논문 371편 · 필터 해제

YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos

2025-06-23 · Haoming Chen, Lichen Yuan, Tianfang Sun, Jingyu Gong 외

3D semantic occupancy prediction in the past was considered to require precise geometric relationships in order to enable effective training. However, in complex indoor environments, the large-scale and widespread collec…

3D Semantic Occupancy PredictionRepresentation LearningSuperpixels

Structural-Spectral Graph Convolution with Evidential Edge Learning for Hyperspectral Image Clustering

2025-06-11 · Jianhan Qi, Yuheng Jia, Hui Liu, Junhui Hou

Hyperspectral image (HSI) clustering assigns similar pixels to the same class without any annotations, which is an important yet challenging task. For large-scale HSIs, most methods rely on superpixel segmentation and pe…

ClusteringContrastive Learninghyperspectral image clusteringImage Clustering+2

Delving Deep into Semantic Relation Distillation

2025-03-27 · Zhaoyi Yan, KangJun Liu, Qixiang Ye

Knowledge distillation has become a cornerstone technique in deep learning, facilitating the transfer of knowledge from complex models to lightweight counterparts. Traditional distillation approaches focus on transferrin…

Knowledge DistillationModel CompressionRelationSuperpixels

ForestSplats: Deformable transient field for Gaussian Splatting in the Wild

2025-03-08 · Wongi Park, Myeongseok Nam, Siwon Kim, Sangwoo Jo 외

Recently, 3D Gaussian Splatting (3D-GS) has emerged, showing real-time rendering speeds and high-quality results in static scenes. Although 3D-GS shows effectiveness in static scenes, their performance significantly degr…

Superpixels

USegMix: Unsupervised Segment Mix for Efficient Data Augmentation in Pathology Images

2025-02-22 · Jiamu Wang, Jin Tae Kwak

In computational pathology, researchers often face challenges due to the scarcity of labeled pathology datasets. Data augmentation emerges as a crucial technique to mitigate this limitation. In this study, we introduce a…

Cancer ClassificationData AugmentationSuperpixels

LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving

2025-01-07 · Lingdong Kong, Xiang Xu, Youquan Liu, Jun Cen 외

Recent advancements in vision foundation models (VFMs) have revolutionized visual perception in 2D, yet their potential for 3D scene understanding, particularly in autonomous driving applications, remains underexplored. …

Autonomous DrivingContrastive Learningobject-detectionObject Detection+3

Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens

2024-12-06 · Jaihyun Lew, Soohyuk Jang, Jaehoon Lee, Seungryong Yoo 외

Transformers, a groundbreaking architecture proposed for Natural Language Processing (NLP), have also achieved remarkable success in Computer Vision. A cornerstone of their success lies in the attention mechanism, which …

Superpixels

AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos

2024-11-29 · Yuze He, Wang Zhao, Shaohui Liu, Yubin Hu 외

We introduce AlphaTablets, a novel and generic representation of 3D planes that features continuous 3D surface and precise boundary delineation. By representing 3D planes as rectangles with alpha channels, AlphaTablets c…

Superpixels

Superpixel Cost Volume Excitation for Stereo Matching

2024-11-20 · Shanglong Liu, Lin Qi, Junyu Dong, Wenxiang Gu 외

In this work, we concentrate on exciting the intrinsic local consistency of stereo matching through the incorporation of superpixel soft constraints, with the objective of mitigating inaccuracies at the boundaries of pre…

Stereo MatchingSuperpixels

SP${ }^3$ : Superpixel-propagated pseudo-label learning for weakly semi-supervised medical image segmentation

2024-11-18 · Shiman Li, Jiayue Zhao, Shaolei Liu, Xiaokun Dai 외

Deep learning-based medical image segmentation helps assist diagnosis and accelerate the treatment process while the model training usually requires large-scale dense annotation datasets. Weakly semi-supervised medical i…

Image SegmentationMedical Image SegmentationOrgan SegmentationPseudo Label+4

Superpixel-informed Implicit Neural Representation for Multi-Dimensional Data

2024-11-18 · Jiayi Li, XiLe Zhao, Jianli Wang, Chao Wang 외

Recently, implicit neural representations (INRs) have attracted increasing attention for multi-dimensional data recovery. However, INRs simply map coordinates via a multi-layer perception (MLP) to corresponding values, i…

Superpixels

Quantum Information-Empowered Graph Neural Network for Hyperspectral Change Detection

2024-11-12 · Chia-Hsiang Lin, Tzu-Hsuan Lin, Jocelyn Chanussot

Change detection (CD) is a critical remote sensing technique for identifying changes in the Earth's surface over time. The outstanding substance identifiability of hyperspectral images (HSIs) has significantly enhanced t…

Change DetectionGraph Neural NetworkSuperpixels

Superpixel Segmentation: A Long-Lasting Ill-Posed Problem

2024-11-10 · Rémi Giraud, Michaël Clément

For many years, image over-segmentation into superpixels has been essential to computer vision pipelines, by creating homogeneous and identifiable regions of similar sizes. Such constrained segmentation problem would req…

SegmentationSemantic SegmentationSuperpixels

STA-Unet: Rethink the semantic redundant for Medical Imaging Segmentation

2024-10-13 · Vamsi Krishna Vasa, Wenhui Zhu, Xiwen Chen, Peijie Qiu 외

In recent years, significant progress has been made in the medical image analysis domain using convolutional neural networks (CNNs). In particular, deep neural networks based on a U-shaped architecture (UNet) with skip c…

Medical Image AnalysisMedical Image SegmentationOrgan SegmentationSuperpixels

A comprehensive review and new taxonomy on superpixel segmentation

2024-09-27 · ACM Surveys 2024 4 · I. B. Barcelos, F. de C. Belém, L. de M. João, Z. K. G. do Patrocínio Jr. 외

Superpixel segmentation consists of partitioning images into regions composed of similar and connected pixels. Its methods have been widely used in many computer vision applications since it allows for reducing the workl…

Superpixels

A novel application of Shapley values for large multidimensional time-series data: Applying explainable AI to a DNA profile classification neural network

2024-09-26 · Lauren Elborough, Duncan Taylor, Melissa Humphries

The application of Shapley values to high-dimensional, time-series-like data is computationally challenging - and sometimes impossible. For $N$ inputs the problem is $2^N$ hard. In image processing, clusters of pixels, r…

ClassificationSuperpixelsTime Series

How to Identify Good Superpixels for Deforestation Detection on Tropical Rainforests

2024-09-06 · Isabela Borlido, Eduardo Bouhid, Victor Sundermann, Hugo Resende 외

The conservation of tropical forests is a topic of significant social and ecological relevance due to their crucial role in the global ecosystem. Unfortunately, deforestation and degradation impact millions of hectares a…

Superpixels

Lagrangian Motion Fields for Long-term Motion Generation

2024-09-03 · Yifei Yang, Zikai Huang, Chenshu Xu, Shengfeng He

Long-term motion generation is a challenging task that requires producing coherent and realistic sequences over extended durations. Current methods primarily rely on framewise motion representations, which capture only s…

Motion GenerationSuperpixels

From Pixels to Objects: A Hierarchical Approach for Part and Object Segmentation Using Local and Global Aggregation

2024-09-02 · Yunfei Xie, Cihang Xie, Alan Yuille, Jieru Mei

In this paper, we introduce a hierarchical transformer-based model designed for sophisticated image segmentation tasks, effectively bridging the granularity of part segmentation with the comprehensive scope of object seg…

Computational EfficiencyImage SegmentationObjectSegmentation+2

ESA: Annotation-Efficient Active Learning for Semantic Segmentation

2024-08-24 · Jinchao Ge, Zeyu Zhang, Minh Hieu Phan, BoWen Zhang 외

Active learning enhances annotation efficiency by selecting the most revealing samples for labeling, thereby reducing reliance on extensive human input. Previous methods in semantic segmentation have centered on individu…

Active LearningSemantic SegmentationSuperpixels
1–20 / 371 다음 →