English
Related papers

Related papers: To Adapt or Not to Adapt? Real-Time Adaptation for…

200 papers

Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be surprisingly poor under domain shifts that appear mild to a…

Computer Vision and Pattern Recognition · Computer Science 2016-12-09 Judy Hoffman , Dequan Wang , Fisher Yu , Trevor Darrell

The majority of learning-based semantic segmentation methods are optimized for daytime scenarios and favorable lighting conditions. Real-world driving scenarios, however, entail adverse environmental conditions such as nighttime…

Computer Vision and Pattern Recognition · Computer Science 2020-03-11 Johan Vertens , Jannik Zürn , Wolfram Burgard

Domain adaptation is a sub-field of machine learning that involves transferring knowledge from a source domain to perform the same task in the target domain. It is a typical challenge in machine learning that arises, e.g., when data is…

Machine Learning · Computer Science 2025-01-09 Philipp Spitzer , Dominik Martin , Laurin Eichberger , Niklas Kühl

Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Mikel Menta , Adriana Romero , Joost van de Weijer

Adapter layers are lightweight, learnable units inserted between transformer layers. Recent work explores using such layers for neural machine translation (NMT), to adapt pre-trained models to new domains or language pairs, training only a…

Computation and Language · Computer Science 2021-10-20 Asa Cooper Stickland , Alexandre Bérard , Vassilina Nikoulina

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Swami Sankaranarayanan , Yogesh Balaji , Arpit Jain , Ser Nam Lim , Rama Chellappa

Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic Unsupervised domain…

Computer Vision and Pattern Recognition · Computer Science 2024-01-03 Serban Stan , Mohammad Rostami

This paper proposes an unsupervised cross-modality domain adaptation approach based on pixel alignment and self-training. Pixel alignment transfers ceT1 scans to hrT2 modality, helping to reduce domain shift in the training segmentation…

Computer Vision and Pattern Recognition · Computer Science 2021-09-30 Hexin Dong , Fei Yu , Jie Zhao , Bin Dong , Li Zhang

Domain adaptation for semantic segmentation across datasets consisting of the same categories has seen several recent successes. However, a more general scenario is when the source and target datasets correspond to non-overlapping label…

Computer Vision and Pattern Recognition · Computer Science 2022-08-05 Tarun Kalluri , Manmohan Chandraker

Transformers are ubiquitous in Natural Language Processing (NLP) tasks, but they are difficult to be deployed on hardware due to the intensive computation. To enable low-latency inference on resource-constrained hardware platforms, we…

Computation and Language · Computer Science 2024-04-05 Hanrui Wang , Zhanghao Wu , Zhijian Liu , Han Cai , Ligeng Zhu , Chuang Gan , Song Han

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…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Tuan-Hung Vu , Himalaya Jain , Maxime Bucher , Matthieu Cord , Patrick Pérez

Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Enming Zhang , Zhengyu Li , Yanru Wu , Jingge Wang , Yang Tan , Guan Wang , Yang Li , Xiaoping Zhang

LiDAR semantic segmentation provides 3D semantic information about the environment, an essential cue for intelligent systems during their decision making processes. Deep neural networks are achieving state-of-the-art results on large public…

Computer Vision and Pattern Recognition · Computer Science 2021-12-06 Inigo Alonso , Luis Riazuelo , Luis Montesano , Ana C. Murillo

Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus on fine-tuning or training the entire or part of the model…

Computation and Language · Computer Science 2022-04-28 Pedro Henrique Martins , Zita Marinho , André F. T. Martins

Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data. Most of existing methods use global-level feature alignment to transfer the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-10 Yikai Bian , Le Hui , Jianjun Qian , Jin Xie

Semantic segmentation is a critical step in automated image interpretation and analysis where pixels are classified into one or more predefined semantically meaningful classes. Deep learning approaches for semantic segmentation rely on…

Computer Vision and Pattern Recognition · Computer Science 2023-07-10 Tushar Kataria , Beatrice Knudsen , Shireen Elhabian

Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Wenyu Zhang , Li Shen , Wanyue Zhang , Chuan-Sheng Foo

Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning methods require large amounts of labeled data for training. Manual annotation is expensive, while simulators can…

Computer Vision and Pattern Recognition · Computer Science 2022-08-24 Weihao Yan , Yeqiang Qian , Chunxiang Wang , Ming Yang

Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important multi-modal datasets. In order to leverage multi-modality for domain adaptation,…

Computer Vision and Pattern Recognition · Computer Science 2022-06-23 Maximilian Jaritz , Tuan-Hung Vu , Raoul de Charette , Émilie Wirbel , Patrick Pérez

Decision Transformers (DT) have demonstrated strong performances in offline reinforcement learning settings, but quickly adapting to unseen novel tasks remains challenging. To address this challenge, we propose a new framework, called…

Machine Learning · Computer Science 2023-04-18 Mengdi Xu , Yuchen Lu , Yikang Shen , Shun Zhang , Ding Zhao , Chuang Gan