Deep models trained on large-scale RGB image datasets have shown tremendous success. It is important to apply such deep models to real-world problems. However, these models suffer from a performance bottleneck under illumination changes. Thermal IR cameras are more robust against such changes, and thus can be very useful for the real-world problems. In order to investigate efficacy of combining feature-rich visible spectrum and thermal image modalities, we propose an unsupervised domain adaptation method which does not require RGB-to-thermal image pairs. We employ large-scale RGB dataset MS-COCO as source domain and thermal dataset FLIR ADAS as target domain to demonstrate results of our method. Although adversarial domain adaptation methods aim to align the distributions of source and target domains, simply aligning the distributions cannot guarantee perfect generalization to the target domain. To this end, we propose a self-training guided adversarial domain adaptation method to promote generalization capabilities of adversarial domain adaptation methods. To perform self-training, pseudo labels are assigned to the samples on the target thermal domain to learn more generalized representations for the target domain. Extensive experimental analyses show that our proposed method achieves better results than the state-of-the-art adversarial domain adaptation methods. The code and models are publicly available.
翻译:在大型 RGB 图像数据集方面受过培训的深层模型显示出巨大的成功, 将这类深层模型应用于现实世界问题非常重要。 但是, 这些模型在光化变化中受到性能瓶颈的影响。 热IR 相机对于这种变化更加强大, 因而对现实世界问题非常有用。 为了调查地貌丰富的可见频谱和热图像模型相结合的功效, 我们建议一种不受监督的域域适应方法, 不需要 RGB 至热图像对配。 我们使用大型 RGB 数据集 MS- CO 作为源域, 热数据集 FLIR ADAS 作为目标域, 以展示我们方法的结果。 虽然对抗性域适应方法旨在协调源和目标域的分布, 只是将分布与目标域相匹配并不能保证完全的通用性。 为此, 我们提议了一种自培训指导的对抗域适应方法, 以促进对抗域适应方法的通用能力。 为了进行自我培训, 我们为目标热域的样品指定了假标签, 以学习目标域域域的更普及化的演示。 广域域域的实验性分析显示我们的拟议方法取得了比目标域域内更好的结果。