• Publications
  • Influence
Going deeper with convolutions
tl;dr
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). Expand
  • 19,776
  • 2646
  • Open Access
SSD: Single Shot MultiBox Detector
tl;dr
This paper presents the first deep network based object detector that does not resample pixels or features for bounding box hypotheses and and is as accurate as approaches that do. Expand
  • 8,152
  • 1838
  • Open Access
Intriguing properties of neural networks
tl;dr
We find that deep neural networks learn input-output mappings that are fairly discontinuous to a significant extend. Expand
  • 5,149
  • 698
  • Open Access
Show and tell: A neural image caption generator
tl;dr
We present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. Expand
  • 3,390
  • 477
  • Open Access
Theano: A Python framework for fast computation of mathematical expressions
tl;dr
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Expand
  • 1,811
  • 135
  • Open Access
Domain Separation Networks
tl;dr
This work was completed while George Trigeorgis was at Google Brain in Mountain View, CA. Expand
  • 597
  • 84
  • Open Access
Challenges in representation learning: A report on three machine learning contests
The ICML 2013 Workshop on Challenges in Representation Learning(1) focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodalExpand
  • 407
  • 84
  • Open Access
An empirical evaluation of deep architectures on problems with many factors of variation
tl;dr
We present a series of experiments which indicate that these models show promise in solving harder learning problems that exhibit many factors of variation. Expand
  • 811
  • 83
  • Open Access
Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
tl;dr
We propose a generative adversarial network (GAN)-based method adapts source-domain images to appear as if drawn from the target domain while maintaining their original content. Expand
  • 720
  • 73
  • Open Access
Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning Challenge
tl;dr
We present a generative model based on a deep recurrent architecture that combines recent advances in computer vision and machine translation and that can be used to generate natural sentences describing an image. Expand
  • 439
  • 68
  • Open Access