Related Experiment Video
Updated: Jan 19, 2026

Visualizing Visual Adaptation
Published on: April 24, 2017
Unsupervised Domain Adaptation for Depth Prediction from Images
Abstract:
State-of-the-art approaches to infer dense depth measurements from images rely on CNNs trained end-to-end on a vast amount of data. However, these approaches suffer a drastic drop in accuracy when dealing with environments much different in appearance and/or context from those observed at training time. This domain shift issue is usually addressed by fine-tuning on smaller sets of images from the target domain annotated with depth labels. Unfortunately, relying on such supervised labeling is seldom feasible in most practical settings. Therefore, we propose an unsupervised domain adaptation technique which does not require groundtruth labels. Our method relies only on image pairs and leverages on classical stereo algorithms to produce disparity measurements alongside with confidence estimators to assess upon their reliability. We propose to fine-tune both depth-from-stereo as well as depth-from-mono architectures by a novel confidence-guided loss function that handles the measured disparities as noisy labels weighted according to the estimated confidence. Extensive experimental results based on standard datasets and evaluation protocols prove that our technique can address effectively the domain shift issue with both stereo and monocular depth prediction architectures and outperforms other state-of-the-art unsupervised loss functions that may be alternatively deployed to pursue domain adaptation.
Related Concept Videos
Conservation of Protein Domains Over Different Proteins
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to...
04:43Visualizing Visual Adaptation
09:43Optimized Setup and Protocol for Magnetic Domain Imaging with In Situ Hysteresis Measurement
16:41A Protocol for Computer-Based Protein Structure and Function Prediction
Predicting Molecular Geometry
08:35Luminescence Lifetime Imaging of O2 with a Frequency-Domain-Based Camera System

