Sort by: Year Popularity Relevance
Ross Girshick, Piotr Dollr, Georgia Gkioxari, Kaiming He - 2017
We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in paralle...
Thomas Brox, Philipp Fischer, Olaf Ronneberger - 2015
There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context...
David Silver, Arthur Guez, Hado van Hasselt - 2015
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively. In particular, we first show th...
Trevor Darrell, Evan Shelhamer, Jonathan Long - 2014
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingl...
Martin Riedmiller, Daan Wierstra, Ioannis Antonoglou, Alex Graves, David Silver, Koray Kavukcuoglu, Volodymyr Mnih - 2013
We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method ...
Daan Wierstra, David Silver, Yuval Tassa, Tom Erez, Nicolas Heess, Alexander Pritzel, Jonathan J. Hunt, Timothy P. Lillicrap - 2015
We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using the same learning algorithm, network architecture and hyper-parameters, our algorithm robustly solves more t...
Karol Zieba, Jake Zhao, Xin Zhang, Jiakai Zhang, Urs Muller, Mathew Monfort, Lawrence D. Jackel, Prasoon Goyal, Beat Flepp, Bernhard Firner, Daniel Dworakowski, Davide Del Testa, Mariusz Bojarski - 2016
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to drive in traffic on local roads with or without lane markings and on highways. It also operates in are...
David Silver, Ioannis Antonoglou, John Quan, Tom Schaul - 2015
Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper ...
Alexander C. Berg, Cheng-Yang Fu, Scott Reed, Christian Szegedy, Dumitru Erhan, Dragomir Anguelov, Wei Liu - 2015
We present a method for detecting objects in images using a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location. At prediction time, the network generates scores for the presence of each object category in e...
Lars Schmidt-Thieme, Zeno Gantner, Christoph Freudenthaler, Steffen Rendle - 2012
Item recommendation is the task of predicting a personalized ranking on a set of items (e.g. websites, movies, products). In this paper, we investigate the most common scenario with implicit feedback (e.g. clicks, purchases). There are many methods for item recommendation from implicit feedback like matrix factorization (MF) or adaptive knearest-...
