Search Results - Deep learning architectures and techniques; Segmentation

Learning What Not to Segment: A New Perspective on Few-Shot Segmentation by Lang, Chunbo, Cheng, Gong, Tu, Binfei, Han, Junwei

“…Recently few-shot segmentation (FSS) has been extensively developed. Most previous works strive to achieve generalization through the meta-learning framework derived from classification tasks…”
Get full text

Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way by Jia, Qi, Yao, Shuilian, Liu, Yu, Fan, Xin, Liu, Risheng, Luo, Zhongxuan

“…It is challenging to accurately detect camouflaged objects from their highly similar surroundings. Existing methods mainly leverage a single-stage detection…”
Get full text

PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images by Zorzi, Stefano, Bazrafkan, Shabab, Habenschuss, Stefan, Fraundorfer, Friedrich

“…While most state-of-the-art instance segmentation methods produce binary segmentation masks, geographic and cartographic applications typically require precise vector polygons of extracted objects…”
Get full text

Deep orientation-aware functional maps: Tackling symmetry issues in Shape Matching by Donati, Nicolas, Corman, Etienne, Ovsjanikov, Maks

“… Using this representation, we propose a new deep learning approach to learn orientation-aware features in afully unsupervised setting…”
Get full text

BoxeR: Box-Attention for 2D and 3D Transformers by Nguyen, Duy-Kien, Ju, Jihong, Booij, Olaf, Oswald, Martin R., Snoek, Cees G. M.

“… module, making it suitable for end-to-end instance detection and segmentation tasks. By learning invariance to rotation in the box-attention module, BoxeR-3D…”
Get full text

Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D MRI Scans with Geometric Deep Neural Networks by Bongratz, Fabian, Rickmann, Anne-Marie, Polsterl, Sebastian, Wachinger, Christian

“… Although traditional and deep learning-based algorithmic pipelines exist for this purpose, they have two major drawbacks…”
Get full text

Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks by Lin, Fanqing, Price, Brian, Martinez, Tony

“…As deep neural networks become the state-of-the-art approach in the field of computer vision for dense prediction tasks, many methods have been developed for automatic estimation of the target outputs…”
Get full text

Image Segmentation Using Text and Image Prompts by Luddecke, Timo, Ecker, Alexander

“…Image segmentation is usually addressed by training a model for a fixed set of object classes…”
Get full text

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation by Zhang, Wenqiang, Huang, Zilong, Luo, Guozhong, Chen, Tao, Wang, Xinggang, Liu, Wenyu, Yu, Gang, Shen, Chunhua

“… Experimental results demonstrate that our method significantly outperforms CNN- and ViT-based networks across several semantic segmentation datasets and achieves a good trade-off between accuracy and latency…”
Get full text

Vision Transformer with Deformable Attention by Xia, Zhuofan, Pan, Xuran, Song, Shiji, Li, Li Erran, Huang, Gao

“…Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models…”
Get full text

Deep Learning Architectures and Techniques for Multi-organ Segmentation by Ogrean, Valentin, Dorobantiu, Alexandru, Brad, Remus

“…Deep learning architectures used for automatic multi-organ segmentation in the medical field have gained increased attention in the last years as the results and achievements outweighed the older techniques…”
Get full text

SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation by Guo, Xiaoqing, Liu, Jie, Liu, Tongliang, Yuan, Yixuan

“… In this paper, we propose a simplex noise transition matrix (SimT) to model the mixed noise distributions in DA semantic segmentation and formulate the problem as estimation of SimT…”
Get full text

Improvements in Forest Segmentation Accuracy Using a New Deep Learning Architecture and Data Augmentation Technique by He, Yan, Jia, Kebin, Wei, Zhihao

“… Accurate monitoring of forest cover is, therefore, essential. Image segmentation networks based on convolutional neural networks have shown significant advantages in remote sensing image analysis with the development of deep learning…”
Get full text

Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation by Gu, Jiaqi, Kwon, Hyoukjun, Wang, Dilin, Ye, Wei, Li, Meng, Chen, Yu-Hsin, Lai, Liangzhen, Chandra, Vikas, Pan, David Z.

“… However, ViTs mainly designed for image classification will generate single-scale low-resolution representations, which makes dense prediction tasks such as semantic segmentation challenging for ViTs…”
Get full text

A state-of-the-art technique to perform cloud-based semantic segmentation using deep learning 3D U-Net architecture by Shaukat, Zeeshan, Farooq, Qurat ul Ain, Tu, Shanshan, Xiao, Chuangbai, Ali, Saqib

“… Using 3D U-net architecture to perform semantic segmentation on brain tumor dataset is at the core of deep learning…”
Get full text

IRv2-Net: A Deep Learning Framework for Enhanced Polyp Segmentation Performance Integrating InceptionResNetV2 and UNet Architecture with Test Time Augmentation Techniques by Ahamed, Md. Faysal, Syfullah, Md. Khalid, Sarkar, Ovi, Islam, Md. Tohidul, Nahiduzzaman, Md, Islam, Md. Rabiul, Khandakar, Amith, Ayari, Mohamed Arselene, Chowdhury, Muhammad E. H.

“… To solve this problem, an automated diagnostic system based on deep learning algorithms is proposed to find polyps…”
Get full text

Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing by Zheng, Qingping, Deng, Jiankang, Zhu, Zheng, Li, Ying, Zafeiriou, Stefanos

“…) produced by the existing state-of-the-art method in face parsing. To tackle these problems, we propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation (DML-CSR) for face parsing…”
Get full text

Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation by Phan, Minh Hieu, Ta, The-Anh, Phung, Son Lam, Tran-Thanh, Long, Bouzerdoum, Abdesselam

“…Deep learning models are known to suffer from the problem of catastrophic forgetting when they incrementally learn new classes…”
Get full text

Dense Learning based Semi-Supervised Object Detection by Chen, Binghui, Li, Pengyu, Chen, Xiang, Wang, Biao, Zhang, Lei, Hua, Xian-Sheng

“… applications anchor-free detectors are more demanded. In this paper, we intend to bridge this gap and propose a DenSe Learning (DSL…”
Get full text

PLAD: Learning to Infer Shape Programs with Pseudo-Labels and Approximate Distributions by Jones, R. Kenny, Walke, Homer, Ritchie, Daniel

“…, and more. Training models to perform this task is complicated because paired (shape, program) data is not readily available for many domains, making exact supervised learning infeasible…”
Get full text