English
Related papers

Related papers: Pixel-by-Pixel Cross-Domain Alignment for Few-Shot…

200 papers

Supervised deep learning requires massive labeled datasets, but obtaining annotations is not always easy or possible, especially for dense tasks like semantic segmentation. To overcome this issue, numerous works explore Unsupervised Domain…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Daniel Morales-Brotons , Grigorios Chrysos , Stratis Tzoumas , Volkan Cevher

Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain are assumed to follow the same distribution and the domain…

Computer Vision and Pattern Recognition · Computer Science 2022-07-27 Zhongying Deng , Kaiyang Zhou , Da Li , Junjun He , Yi-Zhe Song , Tao Xiang

In this study, we investigate the performance of few-shot classification models across different domains, specifically natural images and histopathological images. We first train several few-shot classification models on natural images and…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Ardhendu Sekhar , Aditya Bhattacharya , Vinayak Goyal , Vrinda Goel , Aditya Bhangale , Ravi Kant Gupta , Amit Sethi

Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large source domain for pretraining and transfer the diversity…

Computer Vision and Pattern Recognition · Computer Science 2021-04-15 Utkarsh Ojha , Yijun Li , Jingwan Lu , Alexei A. Efros , Yong Jae Lee , Eli Shechtman , Richard Zhang

Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application. Although there has been a lot of work in this area recently, most of the existing work is based on…

Computer Vision and Pattern Recognition · Computer Science 2020-10-14 Congqi Cao , Yajuan Li , Qinyi Lv , Peng Wang , Yanning Zhang

Semantic segmentation, vital for applications ranging from autonomous driving to robotics, faces significant challenges in domains where collecting large annotated datasets is difficult or prohibitively expensive. In such contexts, such as…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Nico Catalano , Matteo Matteucci

Existing solutions to image editing tasks suffer from several issues. Though achieving remarkably satisfying generated results, some supervised methods require huge amounts of paired training data, which greatly limits their usages. The…

Computer Vision and Pattern Recognition · Computer Science 2024-05-22 Jinshu Chen , Bingchuan Li , Miao Hua , Panpan Xu , Qian He

Domain shift is a very challenging problem for semantic segmentation. Any model can be easily trained on synthetic data, where images and labels are artificially generated, but it will perform poorly when deployed on real environments. In…

Computer Vision and Pattern Recognition · Computer Science 2020-09-03 Luigi Musto , Andrea Zinelli

Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and addresses three common problems: (1) Objects…

Computer Vision and Pattern Recognition · Computer Science 2018-11-21 Holger Caesar , Jasper Uijlings , Vittorio Ferrari

Semantic segmentation networks, which are essential for robotic perception, often suffer from performance degradation when the visual distribution of the deployment environment differs from that of the source dataset on which they were…

Robotics · Computer Science 2026-02-17 Michele Antonazzi , Lorenzo Signorelli , Matteo Luperto , Nicola Basilico

Unsupervised Domain Adaptation (UDA) aims to solve the problem of label scarcity of the target domain by transferring the knowledge from the label rich source domain. Usually, the source domain consists of synthetic images for which the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Anant Khandelwal

Cross-domain few-shot learning (CD-FSL) has drawn increasing attention for handling large differences between the source and target domains--an important concern in real-world scenarios. To overcome these large differences, recent works…

Machine Learning · Computer Science 2022-10-13 Jaehoon Oh , Sungnyun Kim , Namgyu Ho , Jin-Hwa Kim , Hwanjun Song , Se-Young Yun

The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets. However, in realistic scenarios, finding an optimal source…

Machine Learning · Computer Science 2022-12-06 Sandipan Choudhuri , Suli Adeniye , Arunabha Sen , Hemanth Venkateswara

Semantic segmentation is a key problem for many computer vision tasks. While approaches based on convolutional neural networks constantly break new records on different benchmarks, generalizing well to diverse testing environments remains a…

Computer Vision and Pattern Recognition · Computer Science 2019-04-19 Tuan-Hung Vu , Himalaya Jain , Maxime Bucher , Matthieu Cord , Patrick Pérez

Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Still, the common requirement of identical class space shared across domains hinders…

Machine Learning · Computer Science 2022-03-16 Zhangjie Cao , Kaichao You , Ziyang Zhang , Jianmin Wang , Mingsheng Long

Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted. While this might be acceptable in many classification scenarios, it poses a…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Markus Hiller , Rongkai Ma , Mehrtash Harandi , Tom Drummond

We investigate the task of unsupervised domain adaptation in aerial semantic segmentation and discover that the current state-of-the-art algorithms designed for autonomous driving based on domain mixing do not translate well to the aerial…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Edoardo Arnaudo , Antonio Tavera , Fabrizio Dominici , Carlo Masone , Barbara Caputo

Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Despite the effectiveness of self-training techniques in UDA, they struggle to learn each…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Wangkai Li , Rui Sun , Bohao Liao , Zhaoyang Li , Tianzhu Zhang

Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-domain training data (Cross-Domain Few-Shot Learning, CDFSL).…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Shuai Yi , Yixiong Zou , Yuhua Li , Ruixuan Li

In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: The objective is to train a single model that can handle all these domains at test time. Such a…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Antoine Saporta , Tuan-Hung Vu , Matthieu Cord , Patrick Pérez