88 Hits in 3.8 sec

Faster gaze prediction with dense networks and Fisher pruning [article]

Lucas Theis, Iryna Korshunova, Alykhan Tejani, Ferenc Huszár
2018 arXiv   pre-print
Through a combination of knowledge distillation and Fisher pruning, we obtain much more runtime-efficient architectures for saliency prediction, achieving a 10x speedup for the same AUC performance as  ...  We first present a simple yet principled greedy pruning method which we call Fisher pruning.  ...  Faster gaze prediction models also have the potential to speed up the development of video models.  ... 
arXiv:1801.05787v2 fatcat:mm74cf2baregrfcgfzxxd64fki

Training Neural Networks with Fixed Sparse Masks [article]

Yi-Lin Sung, Varun Nair, Colin Raffel
2021 arXiv   pre-print
Our method constructs the mask out of the k parameters with the largest Fisher information as a simple approximation as to which parameters are most important for the task at hand.  ...  In experiments on parameter-efficient transfer learning and distributed training, we show that our approach matches or exceeds the performance of other methods for training with sparse updates while being  ...  Acknowledgments and Disclosure of Funding We thank Yoon Kim, Michael Matena, and Demi Guo for helpful discussions.  ... 
arXiv:2111.09839v1 fatcat:s7mpxtgpuzdrxjjuokwhggf7yu

Differentiable Network Pruning for Microcontrollers [article]

Edgar Liberis, Nicholas D. Lane
2021 arXiv   pre-print
In this work, we present a differentiable structured network pruning method for convolutional neural networks, which integrates a model's MCU-specific resource usage and parameter importance feedback to  ...  Orders of magnitude less storage, memory and computational capacity, compared to what is typically required to execute neural networks, impose strict structural constraints on the network architecture  ...  Faster gaze prediction with dense networks and fisher pruning. arXiv preprint arXiv:1801.05787, 2018. van Amersfoort, J., Alizadeh, M., Farquhar, S., Lane, N., and Gal, Y.  ... 
arXiv:2110.08350v2 fatcat:7jmlafbgzjexbbtdyslmlx6ig4

Recognition of Activities from Eye Gaze and Egocentric Video [article]

Anjith George, Aurobinda Routray
2018 arXiv   pre-print
Image features were extracted using a pre-trained convolutional neural network. Eye and ego-motion are quantized, and the windowed histograms are used as the features.  ...  Three channels of information such as eye movement, ego-motion, and visual features are combined for the classification of activities.  ...  Previous works [20] have used dense SIFT descriptor with PCA in a Bag of words (BoW) framework. Features were extracted from the patch around the point of gaze.  ... 
arXiv:1805.07253v1 fatcat:zthzt2p6ujhpnmzax7zssj7d6y

Iterative multi-path tracking for video and volume segmentation with sparse point supervision [article]

Laurent Lejeune, Jan Grossrieder, Raphael Sznitman
2018 arXiv   pre-print
We show that by collecting 2D locations using a gaze tracker, our approach can provide state-of-the-art segmentations on a range of objects and image modalities (video and 3D volumes), and that these can  ...  It remains a major challenge however to aggregate such datasets, as the time and monetary cost associated with collecting extensive annotations is extremely high.  ...  Acknowledgements This work was supported in part by the Swiss National Science Foundation Grant 200021 162347 and the University of Bern.  ... 
arXiv:1809.00970v1 fatcat:bkyqrz6k4rcadjfxs56jrlc55a

A neurocomputational account of taxonomic responding and fast mapping in early word learning

Julien Mayor, Kim Plunkett
2010 Psychological review  
We show how synapto-genesis supports coherent generalisation of word-object associations and that later synaptic pruning minimises metabolic costs without being detrimental to word learning.  ...  during early childhood and typicality effects observed in lexical development.  ...  In contrast, locally-connected neurones are densely connected and even strong synapto-genesis and pruning would only modulate the magnitude of their interaction.  ... 
doi:10.1037/a0018130 pmid:20063962 fatcat:gqjmauc4hvgm5kfr2jfz4hbo64

A neural window on the emergence of cognition

Rhodri Cusack, Gareth Ball, Christopher D. Smyser, Ghislaine Dehaene-Lambertz
2016 Annals of the New York Academy of Sciences  
These discoveries are changing our understanding of the nature of cognitive networks and their early function, transforming cognitive neuroscience, and opening new windows for education and investigation  ...  We then discuss when white matter tracts mature and when functional brain networks arise. Finally, we assess the responsiveness of these brain systems to external events.  ...  to those observed in adults, with densely connected hubs present in the medial frontal and parietal cortex, precuneus, hippocampus, and insula.  ... 
doi:10.1111/nyas.13036 pmid:27164193 pmcid:PMC4874873 fatcat:kzmevn25hrdbno3bwhuqko5fom

Analysis of the hands in egocentric vision: A survey [article]

Andrea Bandini, José Zariffa
2020 arXiv   pre-print
; and application (e.g., systems that used egocentric hand cues for solving a specific problem). Moreover, a list of the most prominent datasets with hand-based annotations is provided.  ...  in; and developing human-computer interfaces that rely on hand gestures.  ...  The authors would also like to thank Gustavo Balbinot, Guijin Li, and Mehdy Dousty for the helpful discussions and feedback.  ... 
arXiv:1912.10867v2 fatcat:rd2cu3jbkvbvnii5s7fh5c2ncq

Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization [article]

Alexandre Rame, Corentin Dancette, Matthieu Cord
2022 arXiv   pre-print
Our approach is based on the close relations between the gradient covariance, the Fisher Information and the Hessian of the loss: in particular, we show that Fishr eventually aligns the domain-level loss  ...  Notably, Fishr improves the state of the art on the DomainBed benchmark and performs consistently better than Empirical Risk Minimization. Our code is available at  ...  Faster gaze prediction with dense networks and fisher pruning. arXiv preprint, 2018. (p. 6). Thomas, V., Pedregosa, F., van Merriënboer, B., Manzagol, P.-A., Bengio, Y., and Roux, N. L.  ... 
arXiv:2109.02934v3 fatcat:kvujruuh3jgvrc3ik76xvezv4e

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
795 Adaptive Matching of Kernel Means DAY 3 -Jan 14, 2021 Xu, Yi; Pu, Jian; Zhao, Hui 2484 Knowledge Distillation with a Precise Teacher and Prediction with Abstention DAY 3 -Jan 14, 2021  ...  Covariance Representations and Temporal Pruning DAY 2 -Jan 13, 2021 Track 1: AI and Deep Neural Networks PS T1.6 Poster Gather Town 2:00 PM 3:00 PM Enver Sangineto  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Table of Contents

2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
of New South Wales), Bernd Girod (Stanford University), and David Taubman (University of New South Wales) GAN-Based Projector for Faster Recovery With Convergence Guarantees in Linear Inverse Problems  ...  ), Ashish Vaswani (Google Brain), and Jonathon Shlens (Google) MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning 3295 Zechun Liu (HKUST), Haoyuan Mu (Tsinghua University), Xiangyu  ... 
doi:10.1109/iccv.2019.00004 fatcat:5aouo4scprc75c7zetsimylj2y

Computational visual attention systems and their cognitive foundations

Simone Frintrop, Erich Rome, Henrik I. Christensen
2010 ACM Transactions on Applied Perception  
Thus, directing the gaze to a certain region complies with directing a spotlight to a certain part of a dark room [Shulman et al. 1979] .  ...  our gaze, telling where the current action takes place.  ...  For example, Peters and Itti [2008] compared human eye movements with the prediction of a computational attention system in video games.  ... 
doi:10.1145/1658349.1658355 fatcat:tv6pjh7m5zfhjb3pewtci3gtiy

A review of uncertainty quantification in deep learning: Techniques, applications and challenges

Moloud Abdar, Farhad Pourpanah, Sadiq Hussain, Dana Rezazadegan, Li Liu, Mohammad Ghavamzadeh, Paul Fieguth, Xiaochun Cao, Abbas Khosravi, U. Rajendra Acharya, Vladimir Makarenkov, Saeid Nahavandi
2021 Information Fusion  
associated with UQ.  ...  They have been applied to solve a variety of real-world problems in science and engineering.  ...  Acknowledgment This work was partially supported by the Australian Research Council's Discovery Projects funding scheme (project DP190102181) and the Natural Sciences and Engineering Research Council of  ... 
doi:10.1016/j.inffus.2021.05.008 fatcat:yschhguyxbfntftj6jv4dgywxm

A Methodological Review on Prediction of Multi-stage Hypovigilance Detection Systems using Multimodal Features

Qaisar Abbas, Abdullah Alsheddy
2021 IEEE Access  
this project entitled "Analysis and Modeling of Cloud Computing for Drivers Fatigue and Vigilance Monitoring" under the grant no. (0001-008-11-17-3).  ...  ACKNOWLEDGMENT The authors would like to thank King Abdulaziz City for Science and Technology (KACST) and Deanship of Scientific Research center at Al Imam Mohammad ibn Saud Islamic university, for financing  ...  The model involves Depth/Layers 100 of Growth Rate, 12 of dense Blocks, Batch Size of 128, and Initial Learning Rate of 0.1 along with Testing Epochs of 50.  ... 
doi:10.1109/access.2021.3068343 fatcat:rbqdxyabsvah3ginlkd3gqkrwu

Ranking to Learn and Learning to Rank: On the Role of Ranking in Pattern Recognition Applications [article]

Giorgio Roffo
2017 arXiv   pre-print
Moreover, in real-time systems (e.g., visual trackers) ranking approaches are used as optimization procedures which improve the robustness of the system that deals with the high variability of the image  ...  The last decade has seen a revolution in the theory and application of machine learning and pattern recognition.  ...  and faster than ever.  ... 
arXiv:1706.05933v1 fatcat:oc4xtmyqkvf4njpqsojewv75qu
« Previous Showing results 1 — 15 out of 88 results