Rethinking the Inception Architecture for Computer Vision
- Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jonathon Shlens, Z. Wojna
- Computer ScienceComputer Vision and Pattern Recognition
- 2 December 2015
This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Sergey Ioffe, Christian Szegedy
- Computer ScienceInternational Conference on Machine Learning
- 10 February 2015
Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
- Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alexander A. Alemi
- Computer ScienceAAAI Conference on Artificial Intelligence
- 23 February 2016
Clear empirical evidence that training with residual connections accelerates the training of Inception networks significantly is given and several new streamlined architectures for both residual and non-residual Inception Networks are presented.
Probabilistic Linear Discriminant Analysis
- Sergey Ioffe
- Computer ScienceEuropean Conference on Computer Vision
- 7 May 2006
This paper proposes Probabilistic LDA, a generative probability model with which it can both extract the features and combine them for recognition, and shows applications to classification, hypothesis testing, class inference, and clustering.
No Fuss Distance Metric Learning Using Proxies
- Yair Movshovitz-Attias, Alexander Toshev, Thomas Leung, Sergey Ioffe, Saurabh Singh
- Computer ScienceIEEE International Conference on Computer Vision
- 21 March 2017
This paper proposes to optimize the triplet loss on a different space of triplets, consisting of an anchor data point and similar and dissimilar proxy points which are learned as well, and proposes a proxy-based loss which improves on state-of-art results for three standard zero-shot learning datasets.
Deep Convolutional Ranking for Multilabel Image Annotation
- Yunchao Gong, Yangqing Jia, Thomas Leung, Alexander Toshev, Sergey Ioffe
- Computer ScienceInternational Conference on Learning…
- 17 December 2013
It is shown that a significant performance gain could be obtained by combining convolutional architectures with approximate top-$k$ ranking objectives, as thye naturally fit the multilabel tagging problem.
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
- Sergey Ioffe
- Computer Science, BiologyNIPS
- 10 February 2017
This work proposes Batch Renormalization, a simple and effective extension to ensure that the training and inference models generate the same outputs that depend on individual examples rather than the entire minibatch.
Improved Consistent Sampling, Weighted Minhash and L1 Sketching
- Sergey Ioffe
- Computer ScienceIEEE International Conference on Data Mining
- 13 December 2010
A novel method of mapping hashes to short bit-strings, apply it to Weighted Minhash, and achieve more accurate distance estimates from sketches than existing methods, as long as the inputs are sufficiently distinct.
Temporal Differences-Based Policy Iteration and Applications in Neuro-Dynamic Programming
- D. Bertsekas, Sergey Ioffe
- Computer Science
- 1996
We introduce a new policy iteration method for dynamic programming problems with discounted and undiscounted cost. The method is based on the notion of temporal differences, and is primarily geared…
Probabilistic Methods for Finding People
- Sergey Ioffe, D. Forsyth
- Computer ScienceInternational Journal of Computer Vision
- 1 June 2001
This work shows how to find people by finding candidate body segments, and then constructing assemblies of segments that are consistent with the constraints on the appearance of a person that result from kinematic properties, using an efficient projection algorithm for one popular classifier.
...
...