SceneAdapt: Scene-based domain adaptation for semantic segmentation using adversarial learning

by   Daniele Di Mauro, et al.

Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data in order to adapt them to the new domain using fine-tuning. This process is required whenever an already installed camera is moved or a new camera is introduced in a camera network due to the different scene layouts induced by the different viewpoints. To limit the amount of additional training data to be collected, it would be ideal to train a semantic segmentation method using labeled data already available and only unlabeled data coming from the new camera. We formalize this problem as a domain adaptation task and introduce a novel dataset of urban scenes with the related semantic labels. As a first approach to address this challenging task, we propose SceneAdapt, a method for scene adaptation of semantic segmentation algorithms based on adversarial learning. Experiments and comparisons with state-of-the-art approaches to domain adaptation highlight that promising performance can be achieved using adversarial learning both when the two scenes have different but points of view, and when they comprise images of completely different scenes. To encourage research on this topic, we made our code available at our web page:


page 2

page 4

page 12


DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchange

Intelligent vehicles clearly benefit from the expanded Field of View (Fo...

No More Discrimination: Cross City Adaptation of Road Scene Segmenters

Despite the recent success of deep-learning based semantic segmentation,...

Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes

Semantic segmentation, a pixel-level vision task, is developed rapidly b...

Unsupervised Continual Semantic Adaptation through Neural Rendering

An increasing amount of applications rely on data-driven models that are...

Lookahead Adversarial Semantic Segmentation

Semantic segmentation is one of the most fundamental problems in compute...

Semantic Instance Annotation of Street Scenes by 3D to 2D Label Transfer

Semantic annotations are vital for training models for object recognitio...

Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics

Training data is the key ingredient for deep learning approaches, but di...

Please sign up or login with your details

Forgot password? Click here to reset