Related papers: Learning to Adapt for Stereo

Domain adaptation is a crucial and increasingly important task in remote sensing, aiming to transfer knowledge from a source domain a differently distributed target domain. It has broad applications across various real-world applications,…

Deep stereo matching has made significant progress in recent years. However, state-of-the-art methods are based on expensive 4D cost volume, which limits their use in real-world applications. To address this issue, 3D correlation maps and…

Recently there has been substantial interest in spectral methods for learning dynamical systems. These methods are popular since they often offer a good tradeoff between computational and statistical efficiency. Unfortunately, they can be…

End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching. However, existing networks are difficult to use for practical applications since (1) they are memory-hungry and unable to process even…

Stereo matching is one of the longest-standing problems in computer vision with close to 40 years of studies and research. Throughout the years the paradigm has shifted from local, pixel-level decision to various forms of discrete and…

In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e.g. a new centreor a new…

Unsupervised domain adaptation (UDA) is important for applications where large scale annotation of representative data is challenging. For semantic segmentation in particular, it helps deploy on real "target domain" data models that are…

We present a new semi-supervised domain adaptation framework that combines a novel auto-encoder-based domain adaptation model with a simultaneous learning scheme providing stable improvements over state-of-the-art domain adaptation models.…

As deep neural networks are increasingly deployed in dynamic, real-world environments, relying on a single static model is often insufficient. Changes in input data distributions caused by sensor drift or lighting variations necessitate…

Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and…

Recent video depth estimation methods achieve great performance by following the paradigm of image depth estimation, i.e., typically fine-tuning pre-trained video diffusion models with massive data. However, we argue that video depth…

Creating accurate spatial representations that take into account uncertainty is critical for autonomous robots to safely navigate in unstructured environments. Although recent LIDAR based mapping techniques can produce robust occupancy…

Stereo vision is an effective technique for depth estimation with broad applicability in autonomous urban and highway driving. While various deep learning-based approaches have been developed for stereo, the input data from a binocular…

Adaptive filtering algorithms are pervasive throughout signal processing and have had a material impact on a wide variety of domains including audio processing, telecommunications, biomedical sensing, astrophysics and cosmology, seismology,…

For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts. One potential solution is to leverage unlabeled data (e.g., unlabeled LiDAR…

This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground…

A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn't hold in many applications. Instead, ample labeled data might exist in a…

Monocular depth estimation has shown promise in general imaging tasks, aiding in localization and 3D reconstruction. While effective in various domains, its application to bronchoscopic images is hindered by the lack of labeled data,…

Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However, most domain adaptation methods are only restricted to…

We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation…