Single Level Feature-to-Feature Forecasting with Deformable Convolutions

by   Josip Šarić, et al.

Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting. Our method is based on a semantic segmentation model without lateral connections within the upsampling path. Such design ensures that the forecasting addresses only the most abstract features on a very coarse resolution. We further propose to express feature-to-feature forecasting with deformable convolutions. This increases the modelling power due to being able to represent different motion patterns within a single feature map. Experiments show that our models with deformable convolutions outperform their regular and dilated counterparts while minimally increasing the number of parameters. Our method achieves state of the art performance on the Cityscapes validation set when forecasting nine timesteps into the future.



There are no comments yet.


page 10

page 11

page 12

page 15

page 16

page 17


Joint Forecasting of Features and Feature Motion for Dense Semantic Future Prediction

We present a novel dense semantic forecasting approach which is applicab...

Recurrent Flow-Guided Semantic Forecasting

Understanding the world around us and making decisions about the future ...

Adaptable Deformable Convolutions for Semantic Segmentation of Fisheye Images in Autonomous Driving Systems

Advanced Driver-Assistance Systems rely heavily on perception tasks such...

Application of Graph Convolutions in a Lightweight Model for Skeletal Human Motion Forecasting

Prediction of movements is essential for successful cooperation with int...

Future Semantic Segmentation with Convolutional LSTM

We consider the problem of predicting semantic segmentation of future fr...

Vision-Guided Forecasting – Visual Context for Multi-Horizon Time Series Forecasting

Autonomous driving gained huge traction in recent years, due to its pote...

Orientation-aware Semantic Segmentation on Icosahedron Spheres

We address semantic segmentation on omnidirectional images, to leverage ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.