paper-with-me

홈 › Papers

Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images

2019-05-14 · Ivan Krešo, Josip Krapac, Siniša Šegvić

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks. However, the transition to semantic segmentation is hampered by strict memory limitations of contemporary GPUs. The extent of feature map caching required by convolutional backprop poses significant challenges even for moderately sized Pascal images, while requiring careful architectural considerations when the source resolution is in the megapixel range. To address these concerns, we propose a novel DenseNet-based ladder-style architecture which features high modelling power and a very lean upsampling datapath. We also propose to substantially reduce the extent of feature map caching by exploiting inherent spatial efficiency of the DenseNet feature extractor. The resulting models deliver high performance with fewer parameters than competitive approaches, and allow training at megapixel resolution on commodity hardware. The presented experimental results outperform the state-of-the-art in terms of prediction accuracy and execution speed on Cityscapes, Pascal VOC 2012, CamVid and ROB 2018 datasets. Source code will be released upon publication.

📄 PDF Abstract BibTeX arXiv:1905.05661

Code (3)

Maligetzus/Semantic-Segmentation-of-Aerial-Imagery
Maligetzus/Semantic-Segmentation-of-Aerial-Photographs
ivankreso/LDN pytorch

Tasks

image-classificationImage ClassificationSemantic Segmentation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Average Pooling 설명 없음
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Dense Block A Dense Block is a module used in convolutional neural networks that connects *all layers* (with matching feature-map sizes) directly with each other. It was originally…

Similar Papers 제목 키워드 기반

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

2024-03-28 · Donghyun Kim, Byeongho Heo, Dongyoon Han

This paper revives Densely Connected Convolutional Networks (DenseNets) and reveals the underrated effectiveness over predominant ResNet-style architectures. We believe DenseNets' potential was overlooked due to untouche…

Fine-Grained Image ClassificationImage ClassificationInstance Segmentationobject-detection+2

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

2016-11-28 · Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero 외

State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coars…

image-classificationImage SegmentationSegmentationSemantic Segmentation

Robust Semantic Segmentation with Ladder-DenseNet Models

2018-06-09 · Ivan Krešo, Marin Oršić, Petra Bevandić, Siniša Šegvić

We present semantic segmentation experiments with a model capable to perform predictions on four benchmark datasets: Cityscapes, ScanNet, WildDash and KITTI. We employ a ladder-style convolutional architecture featuring …

Semantic Segmentation

LapSeg3D: Weakly Supervised Semantic Segmentation of Point Clouds Representing Laparoscopic Scenes

2022-07-15 · Benjamin Alt, Christian Kunz, Darko Katic, Rayan Younis 외

The semantic segmentation of surgical scenes is a prerequisite for task automation in robot assisted interventions. We propose LapSeg3D, a novel DNN-based approach for the voxel-wise annotation of point clouds representi…

ClusteringSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1

LadderNet: Multi-path networks based on U-Net for medical image segmentation

2018-10-17 · Juntang Zhuang

U-Net has been providing state-of-the-art performance in many medical image segmentation problems. Many modifications have been proposed for U-Net, such as attention U-Net, recurrent residual convolutional U-Net (R2-UNet…

DecoderImage SegmentationMedical Image SegmentationRetinal Vessel Segmentation+2