Filters








3,285 Hits in 4.2 sec

Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation [article]

Cheng Ouyang, Carlo Biffi, Chen Chen, Turkay Kart, Huaqi Qiu, Daniel Rueckert
2020 arXiv   pre-print
CT and MRI, as well as cardiac segmentation for MRI.  ...  Few-shot semantic segmentation (FSS) has great potential for medical imaging applications. Most of the existing FSS techniques require abundant annotated semantic classes for training.  ...  The authors would like to thank Konstantinos Kamnitsas and Zeju Li for insightful comments.  ... 
arXiv:2007.09886v2 fatcat:tnmhky4sn5cv5ojlvglmgvcti4

A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation [article]

Qi Zhao, Binghao Liu, Shuchang Lyu, Xu Wang, Lijiang Chen
2022 arXiv   pre-print
Comprehensive ablation experiments and visualization studies also show the significant effect of SDPM and SAAM for few-shot segmentation task.  ...  Few-shot semantic segmentation is a challenging task of predicting object categories in pixel-wise with only few annotated samples. However, existing approaches still face two main challenges.  ...  ACKNOWLEDGMENT This work was supported by National Natural Science Foundation of China under Grants 62002005 and 62072021.  ... 
arXiv:2108.06600v2 fatcat:nmmjjmmc3bgv7bvc6rlmarb3am

A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data

Hengji Cui, Dong Wei, Kai Ma, Shi Gu, Yefeng Zheng
2020 IEEE Transactions on Medical Imaging  
In this work, we propose a unified framework for generalized low-shot (one- and few-shot) medical image segmentation based on distance metric learning (DML).  ...  In our experiments on brain MRI and abdominal CT datasets, the proposed framework achieves superior performances for low-shot segmentation towards standard DNN-based (3D U-Net) and classical registration-based  ...  Another advantage worth mentioning is that the MRE- Net naturally unifies both one-and few-shot learning with a single framework; in contrast, although extension to few-shot setting is possible for the  ... 
doi:10.1109/tmi.2020.3045775 pmid:33338014 fatcat:vjyusba7fver7i6sk3qfz7k5du

Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning [article]

Yongyi Su, Xun Xu, Kui Jia
2022 arXiv   pre-print
To enable effective updating of multi-prototype classifier weights, we propose two constraints respectively for updating the prototypes w.r.t. all point features and for encouraging the learning of diverse  ...  Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning.  ...  Originated in few-shot learning, multi-prototype learning aims to address the challenging of fitting prototypical network [25] for multi-modal data distribution [5] , [26] , [27] by learning prototypes  ... 
arXiv:2205.03137v1 fatcat:bdu7ytk5pjaqnb62dzhtznnlom

An Artificial Intelligence-Based System to Assess Nutrient Intake for Hospitalised Patients [article]

Ya Lu, Thomai Stathopoulou, Maria F. Vasiloglou, Stergios Christodoulidis, Zeno Stanga, Stavroula Mougiakakou
2020 arXiv   pre-print
The system includes a novel multi-task contextual network for food segmentation, a few-shot learning-based classifier built by limited training samples for food recognition, and an algorithm for 3D surface  ...  This allows sequential food segmentation, recognition, and estimation of the consumed food volume, permitting fully automatic estimation of the nutrient intake for each meal.  ...  ACKNOWLEDGMENT We would like to thank the Central Kitchen of the University Hospital "Inspelspital" and particularly Beat Blum, Thomas Walser, Vinzenz Meier for providing the menus, the recipes and the  ... 
arXiv:2003.08273v1 fatcat:xzyommppebg3bggg3373xiqgi4

Gaussian Prototypical Networks for Few-Shot Learning on Omniglot [article]

Stanislav Fort
2017 arXiv   pre-print
Prototypical networks learn a map between images and embedding vectors, and use their clustering for classification.  ...  We report state-of-the-art performance in 1-shot and 5-shot classification both in 5-way and 20-way regime (for 5-shot 5-way, we are comparable to previous state-of-the-art) on the Omniglot dataset.  ...  Acknowledgements We would like to thank Ben Poole, and Yihui Quek (both at Stanford University) for useful discussions, and brainstorming.  ... 
arXiv:1708.02735v1 fatcat:waumvdlzijggzpidmoma3guzly

Research Progress on Few-Shot Learning for Remote Sensing Image Interpretation

Xian Sun, Bing Wang, Zhirui Wang, Hao Li, Hengchao Li, Kun Fu
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Second, two categories of few-shot learning methods, i.e., the data-augmentation-based and the prior-knowledge-based, are introduced for the interpretation of remote sensing images.  ...  This article gives a reference for scholars working on few-shot learning research in the remote sensing field.  ...  Experimental Datasets This article collects and summarizes the existing published few-shot learning datasets for scene classification, semantic segmentation, and object detection.  ... 
doi:10.1109/jstars.2021.3052869 fatcat:ldos3sx6mvaapjkgsua73l7tve

A Comparative Review of Recent Few-Shot Object Detection Algorithms [article]

Leng Jiaxu, Chen Taiyue, Gao Xinbo, Yu Yongtao, Wang Ye, Gao Feng, Wang Yue
2021 arXiv   pre-print
Few-shot object detection, learning to adapt to the novel classes with a few labeled data, is an imperative and long-lasting problem due to the inherent long-tail distribution of real-world data and the  ...  This survey provides a comprehensive overview from current classic and latest achievements for few-shot object detection to future research expectations from manifold perspectives.  ...  Apart from these surveys for generic few-shot learning, several surveys also put emphasis on specific applications of few-shot learning: COVID-19 diagnosis [66] , natural language processing [67] and  ... 
arXiv:2111.00201v1 fatcat:preckuym7zarndm4yjc7n4k2oi

Space-Time-Brightness Sampling Using an Adaptive Pixel-Wise Coded Exposure

Hajime Nagahara, Dengyu Liu, Toshiki Sonoda, Jinwei Gu
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
A few recent studies have shown that with non-uniform space-time sampling, such as that implemented with pixel-wise coded exposure, one can go beyond this trade-off and achieve high efficiency for scene  ...  We built a prototype camera that enables adaptive coding of patterns online to show the feasibility of the proposed adaptive coded exposure method.  ...  In addition, we built a prototype camera and showed the feasibility of the real-time adaptive coding in real experiments. Our approach and current implementation have a few limitations.  ... 
doi:10.1109/cvprw.2018.00237 dblp:conf/cvpr/NagaharaSLG18 fatcat:wig2tlznyzh4tchjmlncvzd37u

Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction [article]

Ta-Ying Cheng, Hsuan-Ru Yang, Niki Trigoni, Hwann-Tzong Chen, Tyng-Luh Liu
2021 arXiv   pre-print
We present a pose adaptive few-shot learning procedure and a two-stage data interpolation regularization, termed Pose Adaptive Dual Mixup (PADMix), for single-image 3D reconstruction.  ...  We first perform an input mixup which, combined with a pose adaptive learning procedure, is helpful in learning 2D feature extraction and pose adaptive latent encoding.  ...  .; and construction by Learning a Hierarchy of Local and Global Kim, J. 2021. Adaptive Prototype Learning and Allocation Shape Priors.  ... 
arXiv:2112.12484v1 fatcat:ht6sjw4o2zex5hhfi6k4w573ne

Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks [article]

Rebecca Adaimi, Edison Thomaz
2022 arXiv   pre-print
To push this field forward, we build on recent advances in the area of continual machine learning and design a lifelong adaptive learning framework using Prototypical Networks, LAPNet-HAR, that processes  ...  sensor-based data streams in a task-free data-incremental fashion and mitigates catastrophic forgetting using experience replay and continual prototype adaptation.  ...  Leveraging prototypical networks from online continual few-shot learning [14, 42] , our work aims to build and analyze such a system for lifelong adaptive learning in HAR.  ... 
arXiv:2203.05692v1 fatcat:xgtaxzixsrdhhd7xcs7h4y7o7u

What's in a Gist? Towards an Unsupervised Gist Representation for Few-Shot Large Document Classification [chapter]

Jaron Mar, Jiamou Liu
2020 Lecture Notes in Computer Science  
To evaluate our purposed framework, we apply the gist to the task of semantic similarity, specifically to few-shot large document classification where documents on average have a large number of words.  ...  In this paper, we investigate and introduce a novel unsupervised gist extraction and quantification framework that represents a computational form of the gist based on notions from fuzzy trace theory.  ...  MAML: Model-Agnostic Meta-Learning is a few-shot method that meta-learns a prior over model parameters which allows the model to quickly adapt to unseen classes [8] where we set the number of inner steps  ... 
doi:10.1007/978-3-030-47426-3_21 fatcat:hi4syqmc4rcxznfnqq2qgxz33u

UniT: Unified Knowledge Transfer for Any-shot Object Detection and Segmentation [article]

Siddhesh Khandelwal, Raghav Goyal, Leonid Sigal
2021 arXiv   pre-print
Weakly-supervised approaches draw on image-level labels to build detectors/segmentors, while zero/few-shot methods assume abundant instance-level data for a set of base classes, and none to a few examples  ...  Methods for object detection and segmentation rely on large scale instance-level annotations for training, which are difficult and time-consuming to collect.  ...  Few-shot Object Detection and Segmentation Datasets.  ... 
arXiv:2006.07502v3 fatcat:5wtstqlbcfbdplg2qzbpmmyq4a

Wi-Fi-Based Location-Independent Human Activity Recognition with Attention Mechanism Enhanced Method

Xue Ding, Ting Jiang, Yi Zhong, Sheng Wu, Jianfei Yang, Jie Zeng
2022 Electronics  
Specifically, aiming to adapt the model well across locations with quite limited samples, we propose a Channel–Time–Subcarrier Attention Mechanism (CTS-AM) enhanced few-shot learning method that fulfills  ...  Although great success has been achieved for location-dependent recognition tasks, it depends on adequate data collection, which is particularly laborious and time-consuming, being impractical for actual  ...  Finally, an improved prototypical network for a few-shot, learning-based HAR method is presented and analyzed.  ... 
doi:10.3390/electronics11040642 fatcat:mbyqrjr7afdili4nlcpedykpo4

HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning [article]

Andrey Zhmoginov, Mark Sandler, Max Vladymyrov
2022 arXiv   pre-print
In this work we propose a HyperTransformer, a transformer-based model for few-shot learning that generates weights of a convolutional neural network (CNN) directly from support samples.  ...  Finally, we extend our approach to a semi-supervised regime utilizing unlabeled samples in the support set and further improving few-shot performance.  ...  ACKNOWLEDGEMENTS We would like to thank Azalia Mirhoseini, David Ha, Bill Mark, Luke Metz, Raviteja Vemulapalli, Philip Mansfield, and Nolan Miller for insightful discussions.  ... 
arXiv:2201.04182v2 fatcat:vekerijxjffmngdn4oekoulfya
« Previous Showing results 1 — 15 out of 3,285 results