No More Discrimination: Cross City Adaptation of Road Scene Segmenters

Abstract

Despite the recent success of deep-learning based semantic segmentation, deploying a pre-trained road scene segmenter to a city whose images are not presented in the training set would not achieve satisfactory performance due to dataset biases. Instead of collecting a large number of annotated images of each city of interest to train or refine the segmenter, we propose an unsupervised learning approach to adapt road scene segmenters across different cities. By utilizing Google Street View and its timemachine feature, we can collect unannotated images for each road scene at different times, so that the associated static-object priors can be extracted accordingly. By advancing a joint global and class-specific domain adversarial learning framework, adaptation of pre-trained segmenters to that city can be achieved without the need of any user annotation or interaction. We show that our method improves the performance of semantic segmentation in multiple cities across continents, while it performs favorably against state-of-the-art approaches requiring annotated training data.

AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics

“…Transductive transfer learning, often referred to as domain adaptation, is the most common scenario in transfer learning. Various methods have been proposed for adversarial transductive transfer learning in different applications such as image segmentation (Chen et al, 2017), image classification (Tzeng et al, 2017), speech recognition (Hosseini-Asl et al, 2018), domain adaptation under label-shift (Azizzadenesheli et al, 2019), and multiple domain aggregation (Schoenauer-Sebag et al, 2019). The idea of these methods is that features extracted from source and target samples should be similar enough to fool a global discriminator (Tzeng et al, 2017) and/or class-wise discriminators (Chen et al, 2017).…”

“…We designed our experiments to answer the following four questions: (Tzeng et al, 2017) and the method of (Chen et al, 2017), state-of-the-art methods of adversarial transductive transfer learning with global and class-wise discriminators, respectively. For the non-deep learning baseline, we compared AITL to PRECISE (Mourragui et al, 2019), a nondeep learning domain adaptation method specifically designed for pharmacogenomics.…”

“…To answer the second experimental question, AITL was compared to state-of-the-art methods of adversarial and non-deep learning transductive transfer learning, i.e. ADDA (Tzeng et al, 2017), the method of (Chen et al, 2017), and PRECISE (Mourragui et al, 2019), which address the discrepancy only in the input space. AITL achieved significantly better performance in AUROC for all of the drugs and for three out of four drugs in AUPR (the results of (Chen et al, 2017) for Cisplatin were very competitive with AITL).…”

“…ADDA (Tzeng et al, 2017), the method of (Chen et al, 2017), and PRECISE (Mourragui et al, 2019), which address the discrepancy only in the input space. AITL achieved significantly better performance in AUROC for all of the drugs and for three out of four drugs in AUPR (the results of (Chen et al, 2017) for Cisplatin were very competitive with AITL). This indicates that addressing the discrepancies in the both spaces outperforms addressing only the input space discrepancy.…”

“…In the context of drug response prediction, Mourragui et al (Mourragui et al, 2019) proposed PRECISE, a subspace-centric method, based on principal component analysis to minimize the discrepancy in the input space between cell lines and patients. Recently, adversarial domain adaptation has shown great performance in addressing the discrepancy in the input space for different applications, and its performance is comparable to the metric-based and subspace-centric methods in computer vision (Hosseini-Asl et al, 2018;Pinheiro, 2018;Zou et al, 2018;Tsai et al, 2018;Long et al, 2018;Chen et al, 2017;Tzeng et al, 2017;Ganin and Lempitsky, 2014). However, adversarial adaptation that addresses the discrepancies in both the input and output spaces has not yet been explored neither for pharmacogenomics nor for other applications.…”