Search Results for author: Alec Hodgkinson

Found 5 papers, 4 papers with code

DoorGym: A Scalable Door Opening Environment And Baseline Agent

1 code implementation5 Aug 2019 Yusuke Urakami, Alec Hodgkinson, Casey Carlin, Randall Leu, Luca Rigazio, Pieter Abbeel

We introduce DoorGym, an open-source door opening simulation framework designed to utilize domain randomization to train a stable policy.

Explanation-Based Attention for Semi-Supervised Deep Active Learning

no code implementations ICLR Workshop LLD 2019 Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Sotaro Tsukizawa

We introduce an attention mechanism to improve feature extraction for deep active learning (AL) in the semi-supervised setting.

Active Learning

Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions

1 code implementation19 Nov 2018 Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Yasunori Ishii, Sotaro Tsukizawa

We qualitatively and quantitatively show that the proposed explanation method can be used to find image features which cause failures in DNN object detection.

Feature Importance object-detection +1

DNN Feature Map Compression using Learned Representation over GF(2)

1 code implementation ICLR 2018 Denis A. Gudovskiy, Alec Hodgkinson, Luca Rigazio

In this paper, we introduce a method to compress intermediate feature maps of deep neural networks (DNNs) to decrease memory storage and bandwidth requirements during inference.

Dimensionality Reduction General Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.