Fetching the paper…
Reading the bibliography…
This work considers the trade-off between accuracy and test-time computational cost of deep neural networks (DNNs) via \emph{anytime} predictions from auxiliary predictions.
Reasoning about beliefs and actions under computational resource constraints
Horvitz, Eric J · 1987
Earlier work this paper cites.
Solving time-dependent planning problems
Boddy, Mark and Dean, Thomas · 1989
Earlier work this paper cites.
Using anytime algorithms in intelligent systems
Zilberstein, Shlomo · 1996
Earlier work this paper cites.
Rapid Object Detection using a Boosted Cascade of Simple Features
Viola, Paul A. and Jones, Michael J · 2001
Earlier work this paper cites.
Curriculum learning
Bengio, Y., Louradour, J., Collobert, R., and Weston, J · 2009
Earlier work this paper cites.
Learning multiple layers of features from tiny images
Krizhevsky, Alex · 2009
Earlier work this paper cites.
Feature Hashing for Large Scale Multitask Learning
Weinberger, K.Q., Dasgupta, A., Langford, J., Smola, A., and Attenberg, J · 2009
Earlier work this paper cites.
Joint Cascade Optimization Using a Product of Boosted Classifiers
Lefakis, Leonidas and Fleuret, Francois · 2010
Earlier work this paper cites.
Reading digits in natural images with unsupervised feature learning
Netzer, Yuval, Wang, Tao, Coates, Adam, Bissacco, Alessandro, Wu, Bo, and Ng, Andrew Y · 2011
Earlier work this paper cites.
Boosting on a budget: Sampling for feature-efficient prediction
Reyzin, Lev · 2011
Earlier work this paper cites.
Classifier Cascade for Minimizing Feature Evaluation Cost
Chen, Minmin, Weinberger, Kilian Q., Chapelle, Olivier, Kedem, Dor, and Xu, Zhixiang · 2012
Earlier work this paper cites.
SpeedBoost: Anytime Prediction with Uniform Near-Optimality
Grubb, Alexander and Bagnell, J. Andrew · 2012
Earlier work this paper cites.
Timely Object Recognition
Karayev, Sergey, Baumgartner, Tobias, Fritz, Mario, and Darrell, Trevor · 2012
Earlier work this paper cites.
Imagenet classification with deep convolutional neural networks
Krizhevsky, Alex, Sutskever, Ilya, and Hinton, Geoffrey E · 2012
Earlier work this paper cites.
The Greedy Miser: Learning under Test-time Budgets
Xu, Z., Weinberger, K., and Chapelle, O · 2012
Earlier work this paper cites.
Anytime Representation Learning
Xu, Z., Kusner, M., Huang, G., and Weinberger, K. Q · 2013
Cited alongside, same era.
Do deep nets really need to be deep?
Ba, L. J. and Caruana, R · 2014
Cited alongside, same era.
Distilling the knowledge in a neural network
Hinton, Geoffrey, Vinyals, Oriol, and Dean, Jeff · 2014
Cited alongside, same era.
Classifier cascades and trees for minimizing feature evaluation cost
Xu, Z., Kusner, M. J., Weinberger, K. Q., Chen, M., and Chapelle, O · 2014
Cited alongside, same era.
Learning Complexity-Aware Cascades for Deep Pedestrian Detection
Cai, Zhaowei, Saberian, Mohammad J., and Vasconcelos, Nuno · 2015
Cited alongside, same era.
Deeply-supervised nets
Lee, Chen-Yu, Xie, Saining, Gallagher, Patrick W., Zhang, Zhengyou, and Tu, Zhuowen · 2015
Cited alongside, same era.
Xnor-net: Imagenet classification using binary convolutional neural networks
Rastegari, M., Ordonez, V., Redmon, J., and Farhadi, A · 2016
Later among the works it cites.
Adaptive neural networks for fast test-time prediction
Bolukbasi, Tolga, Wang, Joseph, Dekel, Ofer, and Saligrama, Venkatesh · 2017
Closest in time.
Photographic image synthesis with cascaded refinement networks
Chen, Qifeng and Koltun, Vladlen · 2017
Closest in time.
Energy-efficient amortized inference with cascaded deep classifiers
Guan, Jiaqi, Liu, Yang, Liu, Qiang, and Peng, Jian · 2017
Closest in time.
Fractalnet: Ultra-deep neural networks without residuals
Larsson, G., Maire, M., and Shakhnarovich, G · 2017
Closest in time.
Pruning filters for efficient convnets
Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H. P · 2017
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Faster r-cnn: Towards real-time object detection with region proposal networks
Ren, Shaoqing, He, Kaiming, Girshick, Ross B., and Sun, Jian · 2015
Cited alongside, same era.
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, Olga, Deng, Jia, Su, Hao, Krause, Jonathan, Satheesh, Sanjeev, Ma, Sean, Huang, Zhiheng, Karpathy, Andrej, Khosla, Aditya, Bernstein, Michael, Berg, Alexander C., and Fei-Fei, Li · 2015
Cited alongside, same era.
Very deep convolutional networks for large-scale image recognition
Simonyan, Karen and Zisserman, Andrew · 2015
Cited alongside, same era.
Holistically-nested edge detection
Xie, Saining and Tu, Zhuowen · 2015
Cited alongside, same era.
Deep residual learning for image recognition
He, K., Zhang, X., Ren, S., and Sun, J · 2016
Cited alongside, same era.
Efficient feature group sequencing for anytime linear prediction
Hu, Hanzhang, Grubb, Alexander, Hebert, Martial, and Bagnell, J. Andrew · 2016
Cited alongside, same era.
Closest in time.
Learning efficient convolutional networks through network slimming
Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., and Zhang, C · 2017
Closest in time.
Dynamic model selection for prediction under a budget
Nan, Feng and Saligrama, Venkatesh · 2017
Closest in time.
Changing model behavior at test-time using reinforcement
Odena, A., Lawson, D., and Olah, C · 2017
Closest in time.
Inception-v4, inception-resnet and the impact of residual connections on learning
Szegedy, Christian, Ioffe, Sergey, Vanhoucke, Vincent, and Alemi, Alex · 2017
Closest in time.
Convolutional networks with adaptive computation graphs
Veit, Andreas and Belongie, Serge · 2017
Closest in time.
Skipnet: Learning dynamic routing in convolutional networks
Wang, Xin, Yu, Fisher, Dou, Zi-Yi, and Gonzalez, Joseph E · 2017
Closest in time.
Aggregated residual transformations for deep neural networks
Xie, Saining, Girshick, Ross, Dollár, Piotr, Tu, Zhuowen, and He, Kaiming · 2017
Closest in time.
Feedback networks
Zamir, Amir R., Wu, Te-Lin, Sun, Lin, Shen, William, Malik, Jitendra, and Savarese, Silvio · 2017
Closest in time.
Pyramid scene parsing network
Zhao, Hengshuang, Shi, Jianping, Qi, Xiaojuan, Wang, Xiaogang, and Jia, Jiaya · 2017
Closest in time.