Squeeze-and-Excitation Networks

10.1109/TPAMI.2017.2723009

shen, 2016, Places401 and places365 models

huang, 2016, Deep networks with stochastic depth, Proc Eur Conf Comput Vis, 646

krizhevsky, 2009, Learning multiple layers of features from tiny images, Tech Rep, 1

girshick, 2018, Detectron

10.1109/CVPR.2017.668

10.1007/978-3-319-46478-7_29

baker, 2018, Accelerating neural architecture search using performance prediction, Proc Workshop Int Conf Learn Represent

lin, 2014, Microsoft COCO: Common objects in context, Proc Eur Conf Comput Vis, 740

brock, 2018, SMASH: One-shot model architecture search through hypernetworks, Proc Int Conf Learn Representations

10.1109/CVPR.2017.415

cubuk, 2018, Autoaugment: Learning augmentation policies from data, Proc IEEE Conf Comput Vis Pattern Recognit

liu, 2019, DARTS: Differentiable architecture search, Proc Int Conf Learn Represent

elsken, 2019, Efficient multi-objective neural architecture search via lamarckian evolution, Proc Int Conf Learn Represent

10.1609/aaai.v33i01.33014780

real, 2017, Large-scale evolution of image classifiers, Proc Int Conf Mach Learn, 2902

saxena, 2016, Convolutional neural fabrics, Proc Conf Neural Inf Process Syst, 4053

negrinho, 0, Deeparchitect: Automatically designing and training deep architectures, arXiv 1704 08792

liu, 2018, Progressive neural architecture search, Proc Eur Conf Comput Vis, 19

bergstra, 2012, Random search for hyper-parameter optimization, J Mach Learn Res, 13, 281

yang, 2009, Linear spatial pyramid matching using sparse coding for image classification, Proc IEEE Conf Comput Vis Pattern Recognit, 3431

10.1109/TIP.2015.2438548

10.1007/s11263-013-0636-x

nair, 2010, Rectified linear units improve restricted boltzmann machines, Proc 27th Int Conf Mach Learn, 807

jozefowicz, 2015, An empirical exploration of recurrent network architectures, Proc 32nd Int Conf Mach Learn, 37, 2342

howard, 2017, MobileNets: Efficient convolutional neural networks for mobile vision applications, arXiv 1704 04861

10.1007/978-3-642-04277-5_76

10.1109/CVPR.2018.00716

10.1109/ICCV.2015.123

10.1109/ICCV.2017.154

10.5244/C.30.87

gastaldi, 2017, Shake-shake regularization, arXiv 1705 07485

devries, 2017, Improved regularization of convolutional neural networks with cutout, arXiv 1708 04552

10.1109/CVPR.2014.214

krizhevsky, 2012, ImageNet classification with deep convolutional neural networks, Proc Conf Neural Inf Process Syst, 84

10.1109/CVPR.2016.308

10.5244/C.28.88

szegedy, 2016, Inception-v4, inception-resnet and the impact of residual connections on learning, Proc AAAI Conf Artif Intell, 4278

lin, 2014, Network in network, Proc Int Conf Learn Representations

10.1109/CVPR.2017.195

10.1162/106365602320169811

miller, 1989, Designing neural networks using genetic algorithms, Proc 3rd Int Conf Genetic Algorithms, 379

mnih, 2014, Recurrent models of visual attention, Proc Conf Neural Inf Process Syst, 2204

vaswani, 2017, Attention is all you need, Proc Conf Neural Inf Process Syst, 5998

woo, 2018, CBAM: Convolutional block attention module, Proc Eur Conf Comput Vis, 3

10.1109/CVPR.2017.683

10.1109/CVPR.2017.367

10.1109/CVPR.2017.667

xu, 2015, Show, attend and tell: Neural image caption generation with visual attention, Proc Int Conf Mach Learn, 2048

10.1109/ICCV.2015.338

miech, 2017, Learnable pooling with context gating for video classification, Proc IEEE Conf Comput Vis Pattern Recognit

bluche, 2016, Joint line segmentation and transcription for end-to-end handwritten paragraph recognition, Proc Conf Neural Inf Process Syst, 838

10.1007/s11263-015-0816-y

simonyan, 2015, Very deep convolutional networks for large-scale image recognition, Proc Int Conf Learn Representations

baker, 2017, Designing neural network architectures using reinforcement learning, Proc Int Conf Learn Representations

santurkar, 2018, How does batch normalization help optimization? (no, it is not about internal covariate shift), Proc Conf Neural Inf Process Syst, 2483

10.1109/CVPR.2016.90

he, 2016, Identity mappings in deep residual networks, Proc Eur Conf Comput Vis, 630

srivastava, 2015, Training very deep networks, Proc Conf Neural Inf Process Syst, 2377

yosinski, 2014, How transferable are features in deep neural networks?, Proc Conf Neural Inf Process Syst, 3320

chen, 2017, Dual path networks, Proc Conf Neural Inf Process Syst, 4467

10.1145/1553374.1553453

10.1109/CVPR.2017.243

hu, 2018, Gather-excite: Exploiting feature context in convolutional neural networks, Proc Conf Neural Inf Process Syst, 9401

10.1109/CVPR.2017.633

morcos, 2018, On the importance of single directions for generalization, Proc Int Conf Learn Representations

10.1109/CVPR.2017.634

mahajan, 2018, Exploring the limits of weakly supervised pretraining, Proc Eur Conf Comput Vis, 185

ren, 2015, Faster R-CNN: Towards real-time object detection with region proposal networks, Proc 28th Int Conf Neural Inf Process Syst, 1, 91

10.1109/CVPR.2015.7298965

ioffe, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift, Proc 32nd Int Conf Mach Learn, 37, 448

10.1109/CVPR.2015.7298594

newell, 2016, Stacked hourglass networks for human pose estimation, Proc Eur Conf Comput Vis, 483

10.1109/CVPR.2016.314

larochelle, 2010, Learning to combine foveal glimpses with a third-order Boltzmann machine, Proc Conf Neural Inf Process Syst, 1243

jaderberg, 2015, Spatial transformer networks, Proc Conf Neural Inf Process Syst, 2017

10.1523/JNEUROSCI.13-11-04700.1993

tan, 2018, Mnasnet: Platform-aware neural architecture search for mobile, arXiv 1807 11626

10.1038/35058500

10.1109/34.730558

10.1109/CVPR.2018.00907

zoph, 2017, Neural architecture search with reinforcement learning, Proc Int Conf Learn Representations

pham, 2018, Efficient neural architecture search via parameter sharing, Proc Int Conf Mach Learn, 4095

liu, 2018, Hierarchical representations for efficient architecture search, Proc Int Conf Learn Representations