Search · four archives
Search · four archives
20 papers · ranked by Valyu relevance
Mohammed Al-Mukhtar, Ameer Hussein Morad, Mustafa Albadri, MD Samiul Islam
'MD Samiul Islam'] Vision loss happens due to diabetic retinopathy (DR) in severe stages. Thus, an automatic detection method applied to diagnose DR in an earlier phase may help medical doctors to make better decisions. DR is considered one of the main risks, leading to blindness. Computer-Aided Diagnosis systems play…
Junghyo Sohn, Eunjin Jeon, Wonsik Jung, Eunsong Kang + 1 more
Weakly supervised object localization tasks remain challenging to identify and segment an entire object rather than only discriminative parts of the object. To tackle this problem, corruption-based approaches have been devised, which involve the training of non-discriminative regions by corrupting (e.g., erasing) the…
Xiaolin Zhang, Yunchao Wei, Guoliang Kang, Yi Yang + 1 more
Weakly supervised methods usually generate localization results based on attention maps produced by classification networks. However, the attention maps exhibit the most discriminative parts of the object which are small and sparse. We propose to generate Self-produced Guidance (SPG) masks which separate the foreground…
Sangheum Hwang, Hyoeun Kim
Recent advances of deep learning have achieved remarkable performances in various challenging computer vision tasks. Especially in object localization, deep convolutional neural networks outperform traditional approaches based on extraction of data/task-driven features instead of handcrafted features. Although location…
Byeongkeun Kang, Sinhae Cha, Yeejin Lee
Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object localization, which aims to train a neural network capable of predicting both the…
Seunghan Yang, Yoonhyung Kim, Youngeun Kim, Changick Kim
Weakly supervised object localization has recently attracted attention since it aims to identify both class labels and locations of objects by using image-level labels. Most previous methods utilize the activation map corresponding to the highest activation source. Exploiting only one activation map of the highest…
Degaga Wolde Feyisa, Yehualashet Megersa Ayano, Taye Girma Debelee, Friedhelm Schwenker + 2 more
Pulmonary tuberculosis (PTB) is a bacterial infection that affects the lung. PTB remains one of the infectious diseases with the highest global mortalities. Chest radiography is a technique that is often employed in the diagnosis of PTB. Radiologists identify the severity and stage of PTB by inspecting radiographic…
Archith J. Bency, Heesung Kwon, Hyungtae Lee, S. Karthikeyan + 1 more
'B. S. Manjunath'] Abstract. Object localization is an important computer vision problem with a variety of applications. The lack of large scale object-level annotations and the relative abundance of image-level labels makes a compelling case for weak supervision in the object localization task. Deep Convolutional…
Amogh Gudi, Nicolai van Rosmalen, Marco Loog, Jan van Gemert
In the face of scarcity in detailed training annotations, the ability to perform object localization tasks in real-time with weak-supervision is very valuable. However, the computational cost of generating and evaluating region proposals is heavy. We adapt the concept of Class Activation Maps (CAM) [28] into the very…
Xiao Zhou, Shihong Wang, Weiguo Hu, Zhaohao Xie + 4 more
Small object localization is one of the most challenging tasks owing to the poor visual appearance and noisy representation caused by the intrinsic structure of small targets. Recent advances in localizing small objects are mainly dependent on regression-based counting approaches, which require considerable annotations…
Longjie Quan, Dandan Huang, Zhi Liu, Kai Gao + 2 more
Weakly supervised semantic segmentation, based on image-level labels, abandons the pixel-level labels relied upon by traditional semantic segmentation algorithms. It only utilizes images as supervision information, thereby reducing the time cost and human resources required for marking pixel data. The prevailing…
Federico Milani, Nicolò Oreste Pinciroli Vago, Piero Fraternali, Jérémie Sublime + 1 more
'Jérémie Sublime' 'Hélène Urien'] Object Detection requires many precise annotations, which are available for natural images but not for many non-natural data sets such as artworks data sets. A solution is using Weakly Supervised Object Detection (WSOD) techniques that learn accurate object localization from…
Aditya Vora, Shanmuganathan Raman
—This paper addresses the problem of unsupervised object localization in an image. Unlike previous supervised and weakly supervised algorithms that require bounding box or image level annotations for training classifiers in order to learn features representing the object, we propose a simple yet effective technique for…
Hirofumi Kobayashi, Keith C. Cheveralls, Manuel D. Leonetti, Loic A. Royer
Elucidating the diversity and complexity of protein localization is essential to fully understand cellular architecture. Here, we present cytoself, a deep-learning approach for fully self-supervised protein localization profiling and clustering. cytoself leverages a self-supervised training scheme that does not require…
Ofri Goldenberg, Tal Daniel, Dafei Xiao, Yael Shalev Ezra + 2 more
Localization microscopy has overcome the diffraction limit, i.e. the conventional resolution limit of a microscope, enabling nanoscale biological imaging by precisely determining the positions of individual emitters such as single fluorescent molecules. However, the performance of deep learning methods, commonly…
Alex X Lu, Oren Z Kraus, Sam Cooper, Alan M Moses
We introduce an unsupervised deep learning method that learns features for representing single cells in fluorescence microscopy images. Our method exploits the powerful capacity of convolutional neural networks in learning image features, by training networks on a simple self-supervised task that leverages the…
Hang Hu, Jyothsna Padmakumar Bindu, Julia Laskin
Mass spectrometry imaging (MSI) is widely used for the label-free molecular mapping of biological samples. The identification of co-localized molecules in MSI data is crucial to the understanding of biochemical pathways. However, complex MSI data are too large for manual annotation but too small for training deep…
Guo-Hua Yuan, Jinzhe Li, Zejun Yang, Yao-Qi Chen + 5 more
Protein sequence determines not only its structure but also its subcellular localization. Although a series of artificial intelligence models have been reported to predict protein subcellular localization, most of them provide only textual outputs. Here, we present deepGPS, a deep generative model for protein…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Joerg Schnitzbauer, Yina Wang, Matthew Bakalar, Baohui Chen + 3 more
Super-resolution images reconstructed from single-molecule localizations can reveal cellular structures close to the macromolecular scale and are now being used routinely in many biomedical research applications. However, because of their coordinate-based representation, a widely applicable and unified analysis…