Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night

Abstract

Deep learning techniques have enabled the emergence of state-of-the-art models to address object detection tasks. However, these techniques are data-driven, delegating the accuracy to the training dataset which must resemble the images in the target task. The acquisition of a dataset involves annotating images, an arduous and expensive process, generally requiring time and manual effort. Thus, a challenging scenario arises when the target domain of application has no annotated dataset available, making tasks in such situation to lean on a training dataset of a different domain. Sharing this issue, object detection is a vital task for autonomous vehicles where the large amount of driving scenarios yields several domains of application requiring annotated data for the training process. In this work, a method for training a car detection system with annotated data from a source domain (day images) without requiring the image annotations of the target domain (night images) is presented. For that, a model based on Generative Adversarial Networks (GANs) is explored to enable the generation of an artificial dataset with its respective annotations. The artificial dataset (fake dataset) is created translating images from day-time domain to night-time domain. The fake dataset, which comprises annotated images of only the target domain (night images), is then used to train the car detector model. Experimental results showed that the proposed method achieved significant and consistent improvements, including the increasing by more than 10% of the detection performance when compared to the training with only the available annotated data (i.e., day images).

Unsupervised Domain Adaptation of Object Detectors: A Survey

“…Arruda et al [112] Zhang et al [110] Graph reasoning Xu et al [97] Zhao et al [95] Sovinay et al [104]…”

“…Furthermore, with progressive adaptation [64], they showed that applying gradient reversal at only image-level is sufficient for adaptation rather than applying both image-level and instance-level losses. Arruda et al [112] utilized the image translation module to specifically address the domain gap between daylight (source domain) and night-time (target domain) data, as shown in Fig. 20.…”

Feature Enhancement Based on CycleGAN for Nighttime Vehicle Detection

“…In recent years, CNN-based methods are increasingly developed in the research field of vehicle detection at night. [20]- [23] used GAN-based data augmentation methods to expand the training dataset for improving the performance of the detector. Cai et al [19] combined visual saliency and prior information to generate ROIs and used CNN as a classifier.…”

Hierarchical Domain-Consistent Network For Cross-Domain Object Detection

“…[21] and V. F. Arruda et.al. [1] proposed a generator network to further learn the feature difference between the source and target domains. These methods have achieved promising results in some specific scenes.…”