English
Related papers

Related papers: GCISG: Guided Causal Invariant Learning for Improv…

200 papers

Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: training data and test data have different distributions, and the training…

Machine Learning · Computer Science 2018-07-24 Ya Li , Mingming Gong , Xinmei Tian , Tongliang Liu , Dacheng Tao

Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods focus on learning domain invariance, however, such methods overlook the potential inherent in…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Shaocong Long , Qianyu Zhou , Xiangtai Li , Chenhao Ying , Yunhai Tong , Lizhuang Ma , Yuan Luo , Dacheng Tao

Existing domain generalization (DG) methods for cross-person generalization tasks often face challenges in capturing intra- and inter-domain style diversity, resulting in domain gaps with the target domain. In this study, we explore a novel…

Machine Learning · Computer Science 2024-07-02 Junru Zhang , Lang Feng , Zhidan Liu , Yuhan Wu , Yang He , Yabo Dong , Duanqing Xu

Generalized Category Discovery (GCD) aims to classify test-time samples into either seen categories** -- available during training -- or novel ones, without relying on label supervision. Most existing GCD methods assume simultaneous access…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Vaibhav Rathore , Divyam Gupta , Biplab Banerjee

Automating quality inspection with computer vision techniques is often a very data-demanding task. Specifically, supervised deep learning requires a large amount of annotated images for training. In practice, collecting and annotating such…

Computer Vision and Pattern Recognition · Computer Science 2022-02-28 Antoine Cordier , Pierre Gutierrez , Victoire Plessis

Convolutional Neural Networks (CNNs) show impressive performance in the standard classification setting where training and testing data are drawn i.i.d. from a given domain. However, CNNs do not readily generalize to new domains with…

Computer Vision and Pattern Recognition · Computer Science 2020-07-13 Nathan Somavarapu , Chih-Yao Ma , Zsolt Kira

Deep learning models for computer vision often suffer from poor generalization when deployed in real-world settings, especially when trained on synthetic data due to the well-known Sim2Real gap. Despite the growing popularity of style…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Dustin Eisenhardt , Timothy Schaumlöffel , Alperen Kantarci , Gemma Roig

Dataset Distillation aims to distill an entire dataset's knowledge into a few synthetic images. The idea is to synthesize a small number of synthetic data points that, when given to a learning algorithm as training data, result in a model…

Computer Vision and Pattern Recognition · Computer Science 2023-05-05 George Cazenavette , Tongzhou Wang , Antonio Torralba , Alexei A. Efros , Jun-Yan Zhu

Intrinsic image decomposition is a challenging, long-standing computer vision problem for which ground truth data is very difficult to acquire. We explore the use of synthetic data for training CNN-based intrinsic image decomposition…

Computer Vision and Pattern Recognition · Computer Science 2018-12-07 Zhengqi Li , Noah Snavely

As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Zhe Li , Sarah Cechnicka , Cheng Ouyang , Katharina Breininger , Peter Schüffler , Bernhard Kainz

Semantic segmentation algorithms require access to well-annotated datasets captured under diverse illumination conditions to ensure consistent performance. However, poor visibility conditions at varying illumination conditions result in…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Pranjay Shyam , Antyanta Bangunharcana , Kuk-Jin Yoon , Kyung-Soo Kim

Though convolutional neural networks (CNNs) have demonstrated remarkable ability in learning discriminative features, they often generalize poorly to unseen domains. Domain generalization aims to address this problem by learning from a set…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Kaiyang Zhou , Yongxin Yang , Yu Qiao , Tao Xiang

Learning the causal structure behind data is invaluable for improving generalization and obtaining high-quality explanations. We propose a novel framework, Invariant Structure Learning (ISL), that is designed to improve causal structure…

Machine Learning · Computer Science 2022-06-15 Yunhao Ge , Sercan Ö. Arik , Jinsung Yoon , Ao Xu , Laurent Itti , Tomas Pfister

We describe a novel learning-by-synthesis method for estimating gaze direction of an automated intelligent surveillance system. Recently, progress in learning-by-synthesis has proposed training models on synthetic images, which can…

Computer Vision and Pattern Recognition · Computer Science 2018-10-09 Tongtong Zhao , Yuxiao Yan , Jinjia Peng , Zetian Mi , Xianping Fu

Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various real-world applications. While training-based approaches are effective, they are inherently…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Yanghao Wang , Ziqi Jiang , Zhen Wang , Long Chen

Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes. This includes increasing the occurrence of occlusions or varying environmental and…

Computer Vision and Pattern Recognition · Computer Science 2018-10-03 Alexandra Carlson , Katherine A. Skinner , Ram Vasudevan , Matthew Johnson-Roberson

The generalization with respect to domain shifts, as they frequently appear in applications such as autonomous driving, is one of the remaining big challenges for deep learning models. Therefore, we propose an exemplar-based style synthesis…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Yumeng Li , Dan Zhang , Margret Keuper , Anna Khoreva

In this paper, we propose to use a Conditional Generative Adversarial Network (CGAN) for distilling (i.e. transferring) knowledge from sensor data and enhancing low-resolution target detection. In unconstrained surveillance settings, sensor…

Image and Video Processing · Electrical Eng. & Systems 2018-07-23 Siddharth Roheda , Benjamin S. Riggan , Hamid Krim , Liyi Dai

Classical machine learning techniques often struggle with overfitting and unreliable predictions when exposed to novel conditions. Introducing causality into the modelling process offers a promising way to mitigate these challenges by…

Computational Engineering, Finance, and Science · Computer Science 2025-05-28 David Zapata Gonzalez , Marcel Meyer , Oliver Mueller

Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In…

Computer Vision and Pattern Recognition · Computer Science 2021-01-08 Ajay Kumar Tanwani