635 citations · 796 across the 9 of their papers we have counts for
9 papers
Contrastive Neural Processes for Self-Supervised Learning
Konstantinos Kallidromitis, Denis Gudovskiy, Kazuki Kozuka +2
Recent contrastive methods show significant improvement in self-supervised learning in several domains. In particular, contrastive methods are most effective where data augmentatio…
DoorGym: A Scalable Door Opening Environment And Baseline Agent
Yusuke Urakami, Alec Hodgkinson, Casey Carlin +3
In order to practically implement the door opening task, a policy ought to be robust to a wide distribution of door types and environment settings. Reinforcement Learning (RL) with…
DNN Feature Map Compression using Learned Representation over GF(2)
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. Un…
Path Integral Networks: End-to-End Differentiable Optimal Control
Masashi Okada, Luca Rigazio, Takenobu Aoshima
In this paper, we introduce Path Integral Networks (PI-Net), a recurrent network representation of the Path Integral optimal control algorithm. The network includes both system dyn…
ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks
Denis A. Gudovskiy, Luca Rigazio
In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs). ShiftCNN is based on a power-of-…
TransFlow: Unsupervised Motion Flow by Joint Geometric and Pixel-level Estimation
Stefano Alletto, Davide Abati, Simone Calderara +2
We address unsupervised optical flow estimation for ego-centric motion. We argue that optical flow can be cast as a geometrical warping between two successive video frames and devi…
Similarity Mapping with Enhanced Siamese Network for Multi-Object Tracking
Minyoung Kim, Stefano Alletto, Luca Rigazio
Multi-object tracking has recently become an important area of computer vision, especially for Advanced Driver Assistance Systems (ADAS). Despite growing attention, achieving high…
Deep Clustered Convolutional Kernels
Minyoung Kim, Luca Rigazio
Deep neural networks have recently achieved state of the art performance thanks to new training algorithms for rapid parameter estimation and new regularization methods to reduce o…
Towards Deep Neural Network Architectures Robust to Adversarial Examples
Shixiang Gu, Luca Rigazio
Recent work has shown deep neural networks (DNNs) to be highly susceptible to well-designed, small perturbations at the input layer, or so-called adversarial examples. Taking image…