3 code implementations • 16 May 2020 • Huanru Henry Mao, Shuyang Li, Julian McAuley, Garrison Cottrell
Speech recognition (ASR) and speaker diarization (SD) models have traditionally been trained separately to produce rich conversation transcripts with speaker labels.
no code implementations • 18 Feb 2020 • Yao Qin, Nicholas Frosst, Colin Raffel, Garrison Cottrell, Geoffrey Hinton
There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack.
no code implementations • ICLR 2020 • Yao Qin, Nicholas Frosst, Sara Sabour, Colin Raffel, Garrison Cottrell, Geoffrey Hinton
Then, we diagnose the adversarial examples for CapsNets and find that the success of the reconstructive attack is highly related to the visual similarity between the source and target class.
1 code implementation • 22 Mar 2019 • Yao Qin, Nicholas Carlini, Ian Goodfellow, Garrison Cottrell, Colin Raffel
Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
3 code implementations • 22 May 2018 • Yao Qin, Konstantinos Kamnitsas, Siddharth Ancha, Jay Nanavati, Garrison Cottrell, Antonio Criminisi, Aditya Nori
We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing.
Ranked #5 on Brain Tumor Segmentation on BRATS-2015
no code implementations • 5 May 2017 • Amanda Song, Linjie Li, Chad Atalla, Garrison Cottrell
Humans make complex inferences on faces, ranging from objective properties (gender, ethnicity, expression, age, identity, etc) to subjective judgments (facial attractiveness, trustworthiness, sociability, friendliness, etc).
14 code implementations • 7 Apr 2017 • Yao Qin, Dongjin Song, Haifeng Chen, Wei Cheng, Guofei Jiang, Garrison Cottrell
The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades.
5 code implementations • 27 Feb 2017 • Panqu Wang, Pengfei Chen, Ye Yuan, Ding Liu, Zehua Huang, Xiaodi Hou, Garrison Cottrell
This framework 1) effectively enlarges the receptive fields (RF) of the network to aggregate global information; 2) alleviates what we call the "gridding issue" caused by the standard dilated convolution operation.
Ranked #20 on Semantic Segmentation on PASCAL VOC 2012 test
no code implementations • 26 Apr 2016 • Panqu Wang, Isabel Gauthier, Garrison Cottrell
Our results show that, as in the behavioral data, the correlation between subordinate level face and object recognition accuracy increases as experience grows.
no code implementations • 25 Apr 2016 • Panqu Wang, Garrison Cottrell
Our results suggest that the relative order of importance of using central visual field information is face recognition>object recognition>scene recognition, and vice-versa for peripheral information.
no code implementations • 20 Dec 2013 • Honghao Shan, Garrison Cottrell
The human visual system has a hierarchical structure consisting of layers of processing, such as the retina, V1, V2, etc.