CVPR 2017

Learning from Simulated and Unsupervised Images through Adversarial Training

CVPR 2017 tensorflow/models

With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations.

DOMAIN ADAPTATION GAZE ESTIMATION HAND POSE ESTIMATION IMAGE-TO-IMAGE TRANSLATION

Cognitive Mapping and Planning for Visual Navigation

CVPR 2017 tensorflow/models

The accumulated belief of the world enables the agent to track visited regions of the environment.

VISUAL NAVIGATION

Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks

CVPR 2017 tensorflow/models

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks.

UNSUPERVISED DOMAIN ADAPTATION

Full Resolution Image Compression with Recurrent Neural Networks

CVPR 2017 tensorflow/models

As far as we know, this is the first neural network architecture that is able to outperform JPEG at image compression across most bitrates on the rate-distortion curve on the Kodak dataset images, with and without the aid of entropy coding.

IMAGE COMPRESSION

Speed/accuracy trade-offs for modern convolutional object detectors

CVPR 2017 tensorflow/models

The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform.

OBJECT DETECTION

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

CVPR 2017 tensorflow/models

The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images.

IMAGE SUPER-RESOLUTION

Feature Pyramid Networks for Object Detection

CVPR 2017 facebookresearch/detectron

Feature pyramids are a basic component in recognition systems for detecting objects at different scales.

OBJECT DETECTION