• Publications
  • Influence
Rethinking the Inception Architecture for Computer Vision
TLDR
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
TLDR
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
Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve
Probabilistic Linear Discriminant Analysis
  • S. Ioffe
  • Mathematics, Computer Science
    ECCV
  • 7 May 2006
TLDR
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.
Deep Convolutional Ranking for Multilabel Image Annotation
TLDR
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.
No Fuss Distance Metric Learning Using Proxies
TLDR
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.
Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models
  • S. Ioffe
  • Computer Science, Mathematics
    NIPS
  • 10 February 2017
TLDR
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
  • S. Ioffe
  • Mathematics, Computer Science
    IEEE International Conference on Data Mining
  • 13 December 2010
TLDR
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
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
  • S. Ioffe, D. Forsyth
  • Mathematics, Computer Science
    International Journal of Computer Vision
  • 1 June 2001
TLDR
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.
...
1
2
3
...