English
Related papers

Related papers: Reducing Domain Gap by Reducing Style Bias

200 papers

Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to the poor generalization ability, which limits the real-world applications. The…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Yuyang Zhao , Zhun Zhong , Na Zhao , Nicu Sebe , Gim Hee Lee

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

Current Domain Adaptation (DA) methods based on deep architectures assume that the source samples arise from a single distribution. However, in practice, most datasets can be regarded as mixtures of multiple domains. In these cases…

Computer Vision and Pattern Recognition · Computer Science 2018-05-04 Massimiliano Mancini , Lorenzo Porzi , Samuel Rota Bulò , Barbara Caputo , Elisa Ricci

Generating realistic synthetic microscopy images is critical for training deep learning models in label-scarce environments, such as cell counting with many cells per image. However, traditional domain adaptation methods often struggle to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-15 Mohammad Dehghanmanshadi , Wallapak Tavanapong

Deep Neural Networks (DNNs) suffer from the performance degradation when image appearance shift occurs, especially in ultrasound (US) image segmentation. In this paper, we propose a novel and intuitive framework to remove the appearance…

Image and Video Processing · Electrical Eng. & Systems 2020-02-17 Zhendong Liu , Xin Yang , Rui Gao , Shengfeng Liu , Haoran Dou , Shuangchi He , Yuhao Huang , Yankai Huang , Huanjia Luo , Yuanji Zhang , Yi Xiong , Dong Ni

Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a `texture bias': given an image with both…

Computer Vision and Pattern Recognition · Computer Science 2021-01-28 Md Amirul Islam , Matthew Kowal , Patrick Esser , Sen Jia , Bjorn Ommer , Konstantinos G. Derpanis , Neil Bruce

End-to-end learning methods have achieved impressive results in many areas of computer vision. At the same time, these methods still suffer from a degradation in performance when testing on new datasets that stem from a different…

Computer Vision and Pattern Recognition · Computer Science 2016-03-24 Rahaf Aljundi , Tinne Tuytelaars

Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving. To address this issue, this paper proposes a novel instance…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Sungha Choi , Sanghun Jung , Huiwon Yun , Joanne Kim , Seungryong Kim , Jaegul Choo

Convolutional Neural Networks (CNNs) constitute a class of Deep Learning models which have been used in the recent past to resolve many problems in computer vision, in particular optical flow estimation. Measuring displacement and strain…

Image and Video Processing · Electrical Eng. & Systems 2020-09-10 S. Boukhtache , K. Abdelouahab , F. Berry , B. Blaysat , M. Grediac , F. Sur

The absence of well-structured large datasets in medical computer vision results in decreased performance of automated systems and, especially, of deep learning models. Domain generalization techniques aim to approach unknown domains from a…

Image and Video Processing · Electrical Eng. & Systems 2024-06-04 Nikolaos Spanos , Anastasios Arsenos , Paraskevi-Antonia Theofilou , Paraskevi Tzouveli , Athanasios Voulodimos , Stefanos Kollias

Convolutional Neural Networks (CNNs) have recently emerged as the dominant model in computer vision. If provided with enough training data, they predict almost any visual quantity. In a discrete setting, such as classification, CNNs are not…

Computer Vision and Pattern Recognition · Computer Science 2015-11-25 Deepak Pathak , Philipp Krähenbühl , Stella X. Yu , Trevor Darrell

Domain adaptation tasks such as cross-domain sentiment classification aim to utilize existing labeled data in the source domain and unlabeled or few labeled data in the target domain to improve the performance in the target domain via…

Computation and Language · Computer Science 2022-01-03 Dongbo Xi , Fuzhen Zhuang , Ganbin Zhou , Xiaohu Cheng , Fen Lin , Qing He

In this paper, we present DRANet, a network architecture that disentangles image representations and transfers the visual attributes in a latent space for unsupervised cross-domain adaptation. Unlike the existing domain adaptation methods…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Seunghun Lee , Sunghyun Cho , Sunghoon Im

Spiking neural networks (SNNs) are rich in spatio-temporal dynamics and are suitable for processing event-based neuromorphic data. However, event-based datasets are usually less annotated than static datasets. This small data scale makes…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Xiang He , Dongcheng Zhao , Yang Li , Guobin Shen , Qingqun Kong , Yi Zeng

While deep learning models often achieve strong task performance, their successes are hampered by their inability to disentangle spurious correlations from causative factors, such as when they use protected attributes (e.g., race, gender,…

Machine Learning · Computer Science 2020-11-17 Kurtis Evan David , Qiang Liu , Ruth Fong

Convolutional Neural Network (CNN) recognition rates drop in the presence of noise. We demonstrate a novel method of counteracting this drop in recognition rate by adjusting the biases of the neurons in the convolutional layers according to…

Computer Vision and Pattern Recognition · Computer Science 2017-02-06 James R. Geraci , Parichay Kapoor

In recent works, utilizing a deep network trained on meta-training set serves as a strong baseline in few-shot learning. In this paper, we move forward to refine novel-class features by finetuning a trained deep network. Finetuning is…

Computer Vision and Pattern Recognition · Computer Science 2022-06-06 Ran Tao , Han Zhang , Yutong Zheng , Marios Savvides

Training a deep learning model with artificially generated data can be an alternative when training data are scarce, yet it suffers from poor generalization performance due to a large domain gap. In this paper, we characterize the domain…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Gilhyun Nam , Gyeongjae Choi , Kyungmin Lee

We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a…

Computer Vision and Pattern Recognition · Computer Science 2015-10-20 Deepak Pathak , Philipp Krähenbühl , Trevor Darrell

Despite their remarkable expressibility, convolution neural networks (CNNs) still fall short of delivering satisfactory results on single image dehazing, especially in terms of faithful recovery of fine texture details. In this paper, we…

Image and Video Processing · Electrical Eng. & Systems 2022-01-14 Huan Liu , Jun Chen