English
Related papers

Related papers: Unsupervised Finetuning

200 papers

Unsupervised domain adaptation is effective in leveraging rich information from a labeled source domain to an unlabeled target domain. Though deep learning and adversarial strategy made a significant breakthrough in the adaptability of…

Machine Learning · Computer Science 2020-08-25 You-Wei Luo , Chuan-Xian Ren , Dao-Qing Dai , Hong Yan

This paper presents a novel multi-task learning-based method for unsupervised domain adaptation. Specifically, the source and target domain classifiers are jointly learned by considering the geometry of target domain and the divergence…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Jing Zhang , Wanqing Li , Philip Ogunbona

Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely…

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 David Junhao Zhang , Mutian Xu , Chuhui Xue , Wenqing Zhang , Xiaoguang Han , Song Bai , Mike Zheng Shou

Unsupervised image-to-image translation is a class of computer vision problems which aims at modeling conditional distribution of images in the target domain, given a set of unpaired images in the source and target domains. An image in the…

Computer Vision and Pattern Recognition · Computer Science 2018-11-30 Hadi Kazemi , Sobhan Soleymani , Fariborz Taherkhani , Seyed Mehdi Iranmanesh , Nasser M. Nasrabadi

A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift. This problem is commonly addressed by domain adaptation methods. In this work we introduce a novel deep learning…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Subhankar Roy , Aliaksandr Siarohin , Enver Sangineto , Samuel Rota Bulo , Nicu Sebe , Elisa Ricci

Staining reveals the micro structure of the aspirate while creating histopathology slides. Stain variation, defined as a chromatic difference between the source and the target, is caused by varying characteristics during staining, resulting…

Image and Video Processing · Electrical Eng. & Systems 2022-08-31 Nilanjan Chattopadhyay , Shiv Gehlot , Nitin Singhal

Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Evgenii Zheltonozhskii , Chaim Baskin , Alex M. Bronstein , Avi Mendelson

Self-supervised learning has demonstrated considerable potential in hyperspectral representation, yet its application in cross-domain transfer scenarios remains under-explored. Existing methods, however, still rely on source domain…

Computer Vision and Pattern Recognition · Computer Science 2026-01-27 Jianshu Chao , Tianhua Lv , Qiqiong Ma , Yunfei Qiu , Li Fang , Huifang Shen , Wei Yao

Deep detection approaches are powerful in controlled conditions, but appear brittle and fail when source models are used off-the-shelf on unseen domains. Most of the existing works on domain adaptation simplify the setting and access…

Computer Vision and Pattern Recognition · Computer Science 2022-09-02 F. Cappio Borlino , S. Polizzotto , B. Caputo , T. Tommasi

In recent years, the need for semantic segmentation has arisen across several different applications and environments. However, the expense and redundancy of annotation often limits the quantity of labels available for training in any…

Computer Vision and Pattern Recognition · Computer Science 2019-09-25 Tarun Kalluri , Girish Varma , Manmohan Chandraker , C V Jawahar

Pose guided synthesis aims to generate a new image in an arbitrary target pose while preserving the appearance details from the source image. Existing approaches rely on either hard-coded spatial transformations or 3D body modeling. They…

Computer Vision and Pattern Recognition · Computer Science 2019-10-01 Haitian Zheng , Lele Chen , Chenliang Xu , Jiebo Luo

Generalising deep networks to novel domains without manual labels is challenging to deep learning. This problem is intrinsically difficult due to unpredictable changing nature of imagery data distributions in novel domains. Pre-learned…

Computer Vision and Pattern Recognition · Computer Science 2020-06-09 Jiabo Huang , Shaogang Gong

Representation learning with small labeled data have emerged in many problems, since the success of deep neural networks often relies on the availability of a huge amount of labeled data that is expensive to collect. To address it, many…

Computer Vision and Pattern Recognition · Computer Science 2021-01-05 Guo-Jun Qi , Jiebo Luo

The transition from fitting empirical data to achieving true human utility is fundamentally constrained by a granularity mismatch, where fine-grained autoregressive generation is often supervised by coarse or uniform signals. This position…

Computation and Language · Computer Science 2026-02-10 Zhanming Shen , Zeyu Qin , Jiaqi Hu , Wentao Ye , Hao Chen , Xiaomeng Hu , Haokai Xu , Gang Chen , Yi R. Fung , Haobo Wang

Semi-supervised domain adaptation (SSDA) aims to achieve high predictive performance in the target domain with limited labeled target data by exploiting abundant source and unlabeled target data. Despite its significance in numerous…

Machine Learning · Statistics 2025-07-22 Wooseok Ha , Yuansi Chen

A widespread strategy to obtain a language model that performs well on a target domain is to finetune a pretrained model to perform unsupervised next-token prediction on data from that target domain. Finetuning presents two challenges: (i)…

Machine Learning · Computer Science 2025-05-28 Louis Bethune , David Grangier , Dan Busbridge , Eleonora Gualdoni , Marco Cuturi , Pierre Ablin

Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining representations without explicit labels. When it comes to…

Machine Learning · Computer Science 2023-01-25 Yanchao Sun , Shuang Ma , Ratnesh Madaan , Rogerio Bonatti , Furong Huang , Ashish Kapoor

The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotations…

Computer Vision and Pattern Recognition · Computer Science 2020-07-24 Ning Wang , Wengang Zhou , Yibing Song , Chao Ma , Wei Liu , Houqiang Li

A pretrain-finetune strategy is widely used to reduce the overfitting that can occur when data is insufficient for CNN training. First few layers of a CNN pretrained on a large-scale RGB dataset are capable of acquiring general image…

Computer Vision and Pattern Recognition · Computer Science 2022-04-08 Hyungtae Lee , Sungmin Eum , Heesung Kwon