Filters








15,914 Hits in 5.3 sec

Weakly Supervised Localization using Deep Feature Maps [article]

Archith J. Bency, Heesung Kwon, Hyungtae Lee, S. Karthikeyan, B. S. Manjunath
2016 arXiv   pre-print
This weakly supervised method leverages local spatial and semantic patterns captured in the convolutional layers of classification networks.  ...  In this paper, we describe a novel object localization algorithm which uses classification networks trained on only image labels.  ...  The main contributions of this paper are: -We present a method that tackles the problem of object localization for images in a weakly supervised setting using deep convolutional neural networks trained  ... 
arXiv:1603.00489v2 fatcat:s2yajbnnvjaibfy4kfcqfmmif4

Weakly Supervised Localization Using Deep Feature Maps [chapter]

Archith John Bency, Heesung Kwon, Hyungtae Lee, S. Karthikeyan, B. S. Manjunath
2016 Lecture Notes in Computer Science  
This weakly supervised method leverages local spatial and semantic patterns captured in the convolutional layers of classification networks.  ...  In this paper, we describe a novel object localization algorithm which uses classification networks trained on only image labels.  ...  The main contributions of this paper are: -We present a method that tackles the problem of object localization for images in a weakly supervised setting using deep convolutional neural networks trained  ... 
doi:10.1007/978-3-319-46448-0_43 fatcat:vebsje4usrbwxpjqdtpp2wxhfa

Weakly Supervised Object Localization and Detection: A Survey [article]

Dingwen Zhang, Junwei Han, Gong Cheng, Ming-Hsuan Yang
2021 arXiv   pre-print
As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems  ...  In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets  ...  CLASSIC MODELS In this section, we review the classic approaches that learn weakly supervised object localizer or detector without using deep features.  ... 
arXiv:2104.07918v1 fatcat:dwl6sjfzibdilnvjnrbifp4uke

Soft Proposal Networks for Weakly Supervised Object Localization [article]

Yi Zhu, Yanzhao Zhou, Qixiang Ye, Qiang Qiu, Jianbin Jiao
2017 arXiv   pre-print
In the SP-augmented CNNs, referred to as Soft Proposal Networks (SPNs), iteratively evolved object proposals are generated based on the deep feature maps then projected back, and further jointly optimized  ...  Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training.  ...  Weakly Supervised Activation The weakly supervised learning task is performed by firstly using an spatial pooling layer to aggregate deep feature maps to a feature vector, and connecting such a feature  ... 
arXiv:1709.01829v1 fatcat:jto6wiehrjdvhmr2zaujkpbvou

Weakly Supervised Coupled Networks for Visual Sentiment Analysis

Jufeng Yang, Dongyu She, Yu-Kun Lai, Paul L. Rosin, Ming-Hsuan Yang
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
The second branch utilizes both the holistic and localized information by coupling the sentiment map with deep features for robust classification.  ...  This paper presents a weakly supervised coupled convolutional network with two branches to leverage the localized information.  ...  With this scheme, we can detect the sentiment map using weakly supervised learning, and utilize the localized information for discriminative classification.  ... 
doi:10.1109/cvpr.2018.00791 dblp:conf/cvpr/YangSLR018 fatcat:p7rhgkr55zhsjjsrvojlh2ja4q

Deep Multiscale Convolutional Feature Learning for Weakly Supervised Localization of Chest Pathologies in X-ray Images [chapter]

Suman Sedai, Dwarikanath Mahapatra, Zongyuan Ge, Rajib Chakravorty, Rahil Garnavi
2018 Lecture Notes in Computer Science  
We propose a novel weakly supervised method to localize chest pathologies using class aware deep multiscale feature learning.  ...  Our method leverages intermediate feature maps from CNN layers at different stages of a deep network during the training of a classification model using image level annotations of pathologies.  ...  Therefore, we propose a weakly supervised localization method based on CNN using multiscale learning of feature maps at both shallower and deeper layers.  ... 
doi:10.1007/978-3-030-00919-9_31 fatcat:fudi2rubq5fzdd2lqw2ebc3lsq

Weakly Supervised Learning for Object Localization Based on an Attention Mechanism

Nojin Park, Hanseok Ko
2021 Applied Sciences  
The experimental results indicate that our method surpasses the performance of the existing deep learning models based on weakly supervised object localization.  ...  In particular, we develop an activation-map-based framework to judicially control the attention map in the perception branch by adding a two-feature extractor so that better attention weights can be distributed  ...  Weakly Supervised Learning (WSL) [2] is a machine learning framework that trains a deep learning model using the partial labels of training samples.  ... 
doi:10.3390/app112210953 fatcat:etww3ddvlnhivegxtiuu7zl2gy

WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation

Thibaut Durand, Taylor Mordan, Nicolas Thome, Matthieu Cord
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Our model is trained using only global image labels and is devoted to three main visual recognition tasks: image classification, weakly supervised pointwise object localization and semantic segmentation  ...  features related to different class modalities, and a new way to pool these features to provide a global image prediction required for weakly supervised training.  ...  For weakly supervised pointwise object detection, we extract the region (i.e. neuron in the feature map) with maximum score for each class and use it for point-wise localization, as it is done in [44,  ... 
doi:10.1109/cvpr.2017.631 dblp:conf/cvpr/DurandMTC17 fatcat:f5jcuqf3qvbovcwsu45ypsm72e

CELNet: Evidence Localization for Pathology Images using Weakly Supervised Learning [article]

Yongxiang Huang, Albert C. S. Chung
2019 arXiv   pre-print
To overcome this problem, we propose a weakly supervised learning-based approach that can effectively learn to localize the discriminative evidence for a diagnostic label from weakly labeled training data  ...  or require heavy annotations to achieve object localization.  ...  Deep Supervision Deep supervision [4] is employed to empower the interme- diate layers to learn class-discriminative representations, for building the cancer activation map in a higher  ... 
arXiv:1909.07097v1 fatcat:jlkdftmq4ndqbiqgglbhsq2lxa

Weakly Supervised Instance Segmentation by Deep Community Learning [article]

Jaedong Hwang, Seohyun Kim, Jeany Son, Bohyung Han
2020 arXiv   pre-print
We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks.  ...  segmentation, and feature extraction.  ...  Weakly Supervised Object Detection Weakly Supervised Object Detection (WSOD) aims to localize objects in a scene only with image-level class labels.  ... 
arXiv:2001.11207v3 fatcat:b5wdslbtezf65ezansgzdkisai

Learning Deep Features for Discriminative Localization

Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, Antonio Torralba
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
a fully supervised CNN approach.  ...  While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that can be applied to a variety of tasks.  ...  Weakly-supervised object localization: There have been a number of recent works exploring weaklysupervised object localization using CNNs [1, 16, 2, 15] .  ... 
doi:10.1109/cvpr.2016.319 dblp:conf/cvpr/ZhouKLOT16 fatcat:4mmwelc4xbgr5gf4erobt5cmpi

Learning Deep Features for Discriminative Localization [article]

Bolei Zhou and Aditya Khosla and Agata Lapedriza and Aude Oliva and Antonio Torralba
2015 arXiv   pre-print
a fully supervised CNN approach.  ...  While this technique was previously proposed as a means for regularizing training, we find that it actually builds a generic localizable deep representation that can be applied to a variety of tasks.  ...  Weakly-supervised object localization: There have been a number of recent works exploring weaklysupervised object localization using CNNs [1, 16, 2, 15] .  ... 
arXiv:1512.04150v1 fatcat:zkorupnj6jhi7n2c7lswueg5gq

FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference

Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
FickleNet explores diverse combinations of locations on feature maps created by generic deep neural networks.  ...  Fick-leNet implicitly learns the coherence of each location in the feature maps, resulting in a localization map which identifies both discriminative and other parts of objects.  ...  We use the same background cues as DSRG [12] . We feed the generated localization maps from FickleNet to DSRG as the seed cues for weakly supervised segmentation.  ... 
doi:10.1109/cvpr.2019.00541 dblp:conf/cvpr/LeeKLLY19 fatcat:5fl2t3cdbfcy7lavqvvjuha6o4

WALLACE: Weakly Supervised Learning of Deep Convolutional Neural Networks with Multiscale Evidence

Yongsheng Liu, Wenyu Chen, Hong Qu, Tianlei Wang, Jiangzhou Ji, Kebin Miao
2020 IEEE Access  
This paper presents WALLACE, a new framework of deep convolutional neural networks, which perform ConvNet's pyramidal feature hierarchy for weakly supervised learning.  ...  INDEX TERMS Weakly supervised learning, convolutional neural networks, object localization, object classification, multiscale features.  ...  In particular, to our knowledge, this is the first work that has successfully used ConvNets pyramidal feature hierarchy for weakly supervised learning to improve classification and localization performance  ... 
doi:10.1109/access.2020.2968545 fatcat:gfyc47ou6ragfg336xb2niqqdi

FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference [article]

Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon
2019 arXiv   pre-print
FickleNet explores diverse combinations of locations on feature maps created by generic deep neural networks.  ...  FickleNet implicitly learns the coherence of each location in the feature maps, resulting in a localization map which identifies both discriminative and other parts of objects.  ...  We use the same background cues as DSRG [12] . We feed the generated localization maps from FickleNet to DSRG as the seed cues for weakly supervised segmentation.  ... 
arXiv:1902.10421v2 fatcat:zh33vy5vyrbpxlkhcmj3jxvuq4
« Previous Showing results 1 — 15 out of 15,914 results