English
Related papers

Related papers: MIDAS: Modeling Ground-Truth Distributions with Da…

200 papers

Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data. The issue can be mitigated by using unlabeled data from the target domain at training time, but because data…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Thomas Duboudin , Emmanuel Dellandréa , Corentin Abgrall , Gilles Hénaff , Liming Chen

Purpose: Stereo matching methods that enable depth estimation are crucial for visualization enhancement applications in computer-assisted surgery (CAS). Learning-based stereo matching methods are promising to predict accurate results on…

Computer Vision and Pattern Recognition · Computer Science 2023-02-07 Zixin Yang , Richard Simon , Cristian A. Linte

Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address…

Computer Vision and Pattern Recognition · Computer Science 2020-08-12 Jingyang Zhang , Yao Yao , Zixin Luo , Shiwei Li , Tianwei Shen , Tian Fang , Long Quan

Convolutional neural networks require numerous data for training. Considering the difficulties in data collection and labeling in some specific tasks, existing approaches generally use models pre-trained on a large source domain (e.g.…

Computer Vision and Pattern Recognition · Computer Science 2019-09-06 Zhichen Zhao , Bowen Zhang , Yuning Jiang , Li Xu , Lei Li , Wei-Ying Ma

Exiting deep-learning based dense stereo matching methods often rely on ground-truth disparity maps as the training signals, which are however not always available in many situations. In this paper, we design a simple convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2017-09-05 Yiran Zhong , Yuchao Dai , Hongdong Li

Deep learning-based methods deliver state-of-the-art performance for solving inverse problems that arise in computational imaging. These methods can be broadly divided into two groups: (1) learn a network to map measurements to the signal…

Image and Video Processing · Electrical Eng. & Systems 2023-10-11 Nebiyou Yismaw , Ulugbek S. Kamilov , M. Salman Asif

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Many recent methods focus on…

Supervised deep networks are among the best methods for finding correspondences in stereo image pairs. Like all supervised approaches, these networks require ground truth data during training. However, collecting large quantities of…

Computer Vision and Pattern Recognition · Computer Science 2020-08-24 Jamie Watson , Oisin Mac Aodha , Daniyar Turmukhambetov , Gabriel J. Brostow , Michael Firman

The generalization and performance of stereo matching networks are limited due to the domain gap of the existing synthetic datasets and the sparseness of GT labels in the real datasets. In contrast, monocular depth estimation has achieved…

Computer Vision and Pattern Recognition · Computer Science 2024-11-15 Yuran Wang , Yingping Liang , Hesong Li , Ying Fu

Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. To compensate for the over-parameterized models, numerous regularization techniques have been introduced such as those based on dropout.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Mateusz Michalkiewicz , Masoud Faraki , Xiang Yu , Manmohan Chandraker , Mahsa Baktashmotlagh

Unsupervised stereo matching has garnered significant attention for its independence from costly disparity annotations. Typical unsupervised methods rely on the multi-view consistency assumption for training networks, which suffer…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Chuang-Wei Liu , Mingjian Sun , Cairong Zhao , Hanli Wang , Alexander Dvorkovich , Rui Fan

The proliferation of pretrained models, as a result of advancements in pretraining techniques, has led to the emergence of a vast zoo of publicly available models. Effectively utilizing these resources to obtain models with robust…

Machine Learning · Computer Science 2023-06-06 Yimeng Chen , Tianyang Hu , Fengwei Zhou , Zhenguo Li , Zhiming Ma

Knowledge distillation has been quite popular in vision for tasks like classification and segmentation however not much work has been done for distilling state-of-the-art stereo matching methods despite their range of applications. One of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Rafia Rahim , Samuel Woerz , Andreas Zell

Deep learning has recently been shown to be instrumental in the problem of domain adaptation, where the goal is to learn a model on a target domain using a similar --but not identical-- source domain. The rationale for coupling both…

Machine Learning · Computer Science 2018-08-17 Behrang Mehrparvar , Ricardo Vilalta

Domain generalization aims to build generalized models that perform well on unseen domains when only source domains are available for model optimization. Recent studies have shown that large-scale pre-trained models can enhance domain…

Machine Learning · Computer Science 2023-09-12 Byounggyu Lew , Donghyun Son , Buru Chang

Domain Generalization aims to develop models that can generalize to novel and unseen data distributions. In this work, we study how model architectures and pre-training objectives impact feature richness and propose a method to effectively…

Machine Learning · Computer Science 2025-04-30 Xavier Thomas , Deepti Ghadiyaram

One of the main drawbacks of deep Convolutional Neural Networks (DCNN) is that they lack generalization capability. In this work, we focus on the problem of heterogeneous domain generalization which aims to improve the generalization…

Computer Vision and Pattern Recognition · Computer Science 2020-09-14 Yufei Wang , Haoliang Li , Alex C. Kot

We propose to harness the potential of simulation for the semantic segmentation of real-world self-driving scenes in a domain generalization fashion. The segmentation network is trained without any data of target domains and tested on the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-11 Xiangyu Yue , Yang Zhang , Sicheng Zhao , Alberto Sangiovanni-Vincentelli , Kurt Keutzer , Boqing Gong

Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to…

Computer Vision and Pattern Recognition · Computer Science 2016-12-06 Stepan Tulyakov , Anton Ivanov , Francois Fleuret

Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training. Popular domain alignment methods for domain…

Machine Learning · Computer Science 2022-06-17 Wenyu Zhang , Mohamed Ragab , Chuan-Sheng Foo