Share This Author
Improved Regularization of Convolutional Neural Networks with Cutout
This paper shows that the simple regularization technique of randomly masking out square regions of input during training, which is called cutout, can be used to improve the robustness and overall performance of convolutional neural networks.
- Matthew D. Zeiler, Dilip Krishnan, Graham W. Taylor, R. Fergus
- Computer ScienceIEEE Computer Society Conference on Computer…
- 1 June 2010
This work presents a learning framework where features that capture these mid-level cues spontaneously emerge from image data, based on the convolutional decomposition of images under a spar-sity constraint and is totally unsupervised.
Modeling Human Motion Using Binary Latent Variables
A non-linear generative model for human motion data that uses an undirected model with binary latent variables and real-valued "visible" variables that represent joint angles that makes on-line inference efficient and allows for a simple approximate learning procedure.
The Recurrent Temporal Restricted Boltzmann Machine
The Recurrent TRBM is introduced, which is a very slight modification of the TRBM for which exact inference is very easy and exact gradient learning is almost tractable.
Adaptive deconvolutional networks for mid and high level feature learning
- Matthew D. Zeiler, Graham W. Taylor, R. Fergus
- Computer ScienceInternational Conference on Computer Vision
- 6 November 2011
A hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling, relying on a novel inference scheme that ensures each layer reconstructs the input, rather than just the output of the layer directly beneath, as is common with existing hierarchical approaches.
Learning Confidence for Out-of-Distribution Detection in Neural Networks
This work proposes a method of learning confidence estimates for neural networks that is simple to implement and produces intuitively interpretable outputs, and addresses the problem of calibrating out-of-distribution detectors.
Convolutional Learning of Spatio-temporal Features
A model that learns latent representations of image sequences from pairs of successive images is introduced, allowing it to scale to realistic image sizes whilst using a compact parametrization.
Evaluating the Effects of SARS-CoV-2 Spike Mutation D614G on Transmissibility and Pathogenicity
Factored conditional restricted Boltzmann Machines for modeling motion style
A new model is presented, based on the CRBM, that preserves its most important computational properties and includes multiplicative three-way interactions that allow the effective interaction weight between two units to be modulated by the dynamic state of a third unit.
ModDrop: Adaptive Multi-Modal Gesture Recognition
- N. Neverova, Christian Wolf, Graham W. Taylor, Florian Nebout
- Computer ScienceIEEE Trans. Pattern Anal. Mach. Intell.
- 31 December 2014
The proposed ModDrop training technique ensures robustness of the classifier to missing signals in one or several channels to produce meaningful predictions from any number of available modalities, and demonstrates the applicability of the proposed fusion scheme to modalities of arbitrary nature by experiments on the same dataset augmented with audio.