Virtual to Real Adaptation of Pedestrian Detectors

By Luca Ciampi, Nicola Messina, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato. 2020

38 citations recorded by the source corpus.

Pedestrian detection through Computer Vision is a building block for a multitude of applications. Recently, there has been an increasing interest in convolutional neural network-based architectures to execute such a task. One of these supervised networks’ critical goals is to generalize the knowledge learned during the training phase to new scenarios with different characteristics. A suitably labeled dataset is essential to achieve this purpose. The main problem is that manually annotating a dataset usually requires a lot of human effort, and it is costly. To this end, we introduce ViPeD (Virtual Pedestrian Dataset), a new synthetically generated set of images collected with the highly photo-realistic graphical engine of the video game GTA V (Grand Theft Auto V), where annotations are automatically acquired. However, when training solely on the synthetic dataset, the model experiences a Synthetic2Real domain shift leading to a performance drop when applied to real-world images. To mitigate this gap, we propose two different domain adaptation techniques suitable for the pedestrian detection task, but possibly applicable to general object detection. Experiments show that the network trained with ViPeD can generalize over unseen real-world scenarios better than the detector trained over real-world data, exploiting the variety of our synthetic dataset. Furthermore, we demonstrate that with our domain adaptation techniques, we can reduce the Synthetic2Real domain shift, making the two domains closer and obtaining a performance improvement when testing the network over the real-world images.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Carlos Santiago
2. Giuseppe Amato
3. João Paulo Costeira
4. Claudio Gennaro
5. Luca Ciampi

In Computer Vision and Pattern Recognition

1. Luca Ciampi
2. Giuseppe Amato
3. Claudio Gennaro
4. Carlos Santiago
5. João Paulo Costeira
6. Lourdes de Agapito

In Representation & Self-Supervised Learning

1. Giuseppe Amato
2. Claudio Gennaro
3. Luca Ciampi

Citations in the corpus

• Domain Adaptation for Traffic Density Estimation (2021, methodology): “To the best of our knowledge, this work is the first that employs UDA to the counting task, extending the very preliminary results obtained in (Ciampi et al., 2020b), where a similar approach was exploited in just one limited scenario.”