A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks
[article]
2018
arXiv
pre-print
Preserved Fulltext
We introduce a saliency-based distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task. ...
learns how best to sample from the underlying high resolution data in a manner which preserves task-relevant information better than uniform downsampling. ...
We acknowledge NVIDIA Corporation for hardware donations. ...
arXiv:1809.03355v1
fatcat:awpyqooeprcajoiqxlzvrwnpry
Learning to Zoom: A Saliency-Based Sampling Layer for Neural Networks
[chapter]
2018
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
We introduce a saliency-based distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task. ...
learns how best to sample from the underlying high resolution data in a manner which preserves task-relevant information better than uniform downsampling. ...
We acknowledge NVIDIA Corporation for hardware donations. ...
doi:10.1007/978-3-030-01240-3_4
fatcat:evduc4styfa7plcumsq3wyqjqm
Learning When and Where to Zoom with Deep Reinforcement Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this direction, we propose PatchDrop a reinforcement learning approach to dynamically identify when and where to use/acquire high resolution data conditioned on the paired, cheap, low resolution images ...
For these reasons, it is desirable to develop an automatic method to selectively use high resolution data when necessary while maintaining accuracy and reducing acquisition/run-time cost. ...
Acknowledgements This research was supported by Stanfords Data for Development Initiative and NSF grants 1651565 and 1733686. ...
arXiv:2003.00425v2
fatcat:wh4bslazmngztmx3qwg66enlmu
Learning When and Where to Zoom With Deep Reinforcement Learning
2020
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this direction, we propose PatchDrop a reinforcement learning approach to dynamically identify when and where to use/acquire high resolution data conditioned on the paired, cheap, low resolution images ...
For these reasons, it is desirable to develop an automatic method to selectively use high resolution data when necessary while maintaining accuracy and reducing acquisition/run-time cost. ...
Acknowledgements This research was supported by Stanford's Data for Development Initiative and NSF grants 1651565 and 1733686. ...
doi:10.1109/cvpr42600.2020.01236
dblp:conf/cvpr/UzkentE20
fatcat:x42vmls5pvaj7j4itxq2wqwz3i
Guided Zoom: Questioning Network Evidence for Fine-grained Classification
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The reason/evidence upon which a deep convolutional neural network makes a prediction is defined to be the spatial grounding, in the pixel space, for a specific class conditional probability in the model ...
We show that Guided Zoom improves the classification accuracy of a deep convolutional neural network model and obtains state-of-the-art results on three fine-grained classification benchmark datasets. ...
Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. ...
arXiv:1812.02626v2
fatcat:74dd2h3su5cnfp6xquqgefhd3e
Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization
2022
International Conference on Machine Learning
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To this end, a novel cartoontexture-saliency-sampler (CTSS) module is proposed to dynamically sample cartoon-texturesalient patches from training data. ...
With extensive experiments, we demonstrate that texture saliency adaptive attention in adversarial learning, as a missing ingredient of related methods in image cartoonization, is of significant importance ...
With the thriving of deep neural networks, recent image cartoonization methods resort to learning-based framework, typically generative adversarial network (GAN) (Goodfellow et al., 2014) , to automatically ...
dblp:conf/icml/GaoZT22
fatcat:bjr5qzjp6nfehdsyppu5ka5nly
Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonization
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To this end, a novel cartoon-texture-saliency-sampler (CTSS) module is proposed to dynamically sample cartoon-texture-salient patches from training data. ...
With extensive experiments, we demonstrate that texture saliency adaptive attention in adversarial learning, as a missing ingredient of related methods in image cartoonization, is of significant importance ...
With the thriving of deep neural networks, recent image cartoonization methods resort to learning-based framework, typically generative adversarial network (GAN) [5] , to automatically learn and transfer ...
arXiv:2208.01587v1
fatcat:mxdp45w7efaedb7qli62mkwwtq
Learning how to explain neural networks: PatternNet and PatternAttribution
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Yet they are used on multi-layer networks with millions of parameters. This is a cause for concern since linear models are simple neural networks. ...
DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a linear model. ...
We are grateful to Chris Olah and Gregoire Montavon for the valuable discussions. ...
arXiv:1705.05598v2
fatcat:z4hno2qyk5hdpnrwa6ij74mrb4
Exploring to learn visual saliency: The RL-IAC approach
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
On the one hand, we describe a method for learning and incrementally updating a model of visual saliency from a depth-based object detector. ...
We then demonstrate that such a saliency model learned directly on a robot outperforms several state-of-the-art saliency techniques, and that RL-IAC can drastically decrease the required time for learning ...
ACKNOWLEDGMENT The authors would like to thank the INRIA Flowers team, and especially Pierre-Yves Oudeyer for the valuable help on the IAC aspect. ...
arXiv:1804.00435v1
fatcat:3gcttrpnmnf43pxvizxmxiy2p4
Deep Learning Applied to SEM Images for Supporting Marine Coralline Algae Classification
2021
Diversity
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In this work, we explored a new classification tool for coralline algae, using fine-tuning pretrained Convolutional Neural Networks (CNNs) on SEM images paired to morphological categories, including cell ...
Our model produced promising results in terms of image classification accuracy given the constraint of a limited dataset and was tested for the identification of two ambiguous samples referred to as L. ...
Deep learning usually refers to artificial neural networks with more than two hidden layers. ...
doi:10.3390/d13120640
fatcat:5gtiso2545e2vp2tlujuso7w4q
360-Degree Gaze Estimation in the Wild Using Multiple Zoom Scales
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2009.06924v2 fatcat:xs27uqxgljgb3nny3f7qieufyyOther Versions
In this work, we design a model that mimics humans' ability to estimate the gaze by aggregating from focused looks, each at a different magnification level of the face area. ...
The model avoids the need to extract clear eye patches and at the same time addresses another important issue of face-scale variation for gaze estimation in the wild. ...
Acknowledgement We thank the anonymous reviewers for valuable suggestions. ...
arXiv:2009.06924v3
fatcat:7oult55dozbozaxza5c2syx3ru
What evidence does deep learning model use to classify Skin Lesions?
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we propose a method to interpret the deep learning classification findings. Firstly, we propose an accurate neural network architecture to classify skin lesions. ...
Recent years, the value of deep learning empowered computer-assisted diagnose has been shown in biomedical imaging based decision making. ...
In this paper, we proposed a novel method based on deep convolutional neural networks and low-level image feature descriptors, which imitate clinical criteria representations, to solve skin lesion analysis ...
arXiv:1811.01051v3
fatcat:rg2lhdxo2ngi7gtmjpevc7q6wu
Weakly Supervised Learning Guided by Activation Mapping Applied to a Novel Citrus Pest Benchmark
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this context, we design a weakly supervised learning process guided by saliency maps to automatically select regions of interest in the images, significantly reducing the annotation task. ...
In addition, we create a large citrus pest benchmark composed of positive samples (six classes of mite species) and negative samples. ...
[33] proposed a weakly supervised CNN framework, called Multiple Instance Learning Convolutional Neural Networks (MILCNN), which fuses residual network and multiple instances learning loss layer. ...
arXiv:2004.11252v1
fatcat:dvv3rlj2zjfwnkjvyyfhdxhqla
Pitch Estimation Of Choir Music Using Deep Learning Strategies: From Solo To Unison Recordings
2017
Zenodo
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Then, we train several deep learning architectures to extract pitch infor- mation from monophonic singing voice signals, and adapt them afterwards to model unison performances. ...
The presented models provide a first step towards de automatic transcription of choir singing recordings, and the unison model is a useful resource for choir singing synthesis. ...
To do so, we decided to train a neural network based on the ones we used for the monophonic pitch estimation and adapt it to predict these two values. ...
doi:10.5281/zenodo.1108524
fatcat:ybmgeomdy5fn5nm5j7vgxw2zf4
CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild
2019
International Conference on Learning Representations
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In particular, we learn a camouflage pattern to hide vehicles from being detected by state-of-the-art convolutional neural network based detectors. Our approach alternates between two threads. ...
In the first, we train a neural approximation function to imitate how a simulator applies a camouflage to vehicles and how a vehicle detector performs given images of the camouflaged vehicles. ...
ACKNOWLEDGMENT This work was in part supported by the NSF grants IIS-1212948, IIS-1566511, and a gift from Uber Technologies Inc. ...
dblp:conf/iclr/ZhangFDG19
fatcat:sl2zumsvunejzcyf4422gsjrfe
« Previous
Showing results 1 — 15 out of 1,572 results