English
Related papers

Related papers: One to Transfer All: A Universal Transfer Framewor…

200 papers

Foundation models are multi-dataset and multi-task machine learning methods that once pre-trained can be fine-tuned for a large variety of downstream applications. The successful development of such general-purpose models for physics data…

High Energy Physics - Phenomenology · Physics 2024-09-10 Joschka Birk , Anna Hallin , Gregor Kasieczka

Weight-sharing neural architecture search aims to optimize a configurable neural network model (supernet) for a variety of deployment scenarios across many devices with different resource constraints. Existing approaches use evolutionary…

Machine Learning · Computer Science 2023-07-04 Achintya Kundu , Laura Wynter , Rhui Dih Lee , Luis Angel Bathen

Source-Free Object Detection (SFOD) aims to adapt a source-pretrained object detector to a target domain without access to source data. However, existing SFOD methods predominantly rely on internal knowledge from the source model, which…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Huizai Yao , Sicheng Zhao , Pengteng Li , Yi Cui , Shuo Lu , Weiyu Guo , Yunfan Lu , Yijie Xu , Hui Xiong

Few-shot learning aims to fast adapt a deep model from a few examples. While pre-training and meta-training can create deep models powerful for few-shot generalization, we find that pre-training and meta-training focuses respectively on…

Machine Learning · Computer Science 2022-12-20 Yang Shu , Zhangjie Cao , Jinghan Gao , Jianmin Wang , Philip S. Yu , Mingsheng Long

Transferring knowledge by fine-tuning large-scale pre-trained networks has become a standard paradigm for downstream tasks, yet the knowledge of a pre-trained model is tightly coupled with monolithic architecture, which restricts flexible…

Machine Learning · Computer Science 2026-05-26 Jianlu Shen , Fu Feng , Yucheng Xie , Jiaqi Lv , Xin Geng

Self-supervised fMRI foundation models have shown promising transfer performance, yet most rely on predefined region-level parcellations that discard fine-grained voxel information and introduce atlas-dependent biases. We propose Omni-fMRI,…

Computational Engineering, Finance, and Science · Computer Science 2026-02-02 Mo Wang , Wenhao Ye , Junfeng Xia , Junxiang Zhang , Xuanye Pan , Minghao Xu , Haotian Deng , Hongkai Wen , Quanying Liu

Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data selection critical for training efficiency. Existing methods derive selection signals…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Mingkang Dong , Hongyi Cai , Xiwen Lei , Jie Li , Tao Zhang , Muxin Pu

Foundation models like ChatGPT and Sora that are trained on a huge scale of data have made a revolutionary social impact. However, it is extremely challenging for sensors in many different fields to collect similar scales of natural images…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Chenyang Lei , Liyi Chen , Jun Cen , Xiao Chen , Zhen Lei , Felix Heide , Ziwei Liu , Qifeng Chen , Zhaoxiang Zhang

Although recent Siamese network-based trackers have achieved impressive perceptual accuracy for single object tracking in LiDAR point clouds, they usually utilized heavy correlation operations to capture category-level characteristics only,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Xiantong Zhao , Yinan Han , Shengjing Tian , Jian Liu , Xiuping Liu

Thermal imaging is crucial for scene understanding, particularly in low-light and nighttime conditions. However, collecting large thermal datasets is costly and labor-intensive due to the specialized equipment required for infrared image…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Jay N. Paranjape , Celso de Melo , Vishal M. Patel

This work presents the first attempt to repurpose vision foundation models (VFMs) as image codecs, aiming to explore their generation capability for low-rate image compression. VFMs are widely employed in both conditional and unconditional…

Image and Video Processing · Electrical Eng. & Systems 2025-09-08 Huu-Tai Phung , Yu-Hsiang Lin , Yen-Kuan Ho , Wen-Hsiao Peng

Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability. However, large-scale models…

Computer Vision and Pattern Recognition · Computer Science 2022-12-09 Di Wang , Qiming Zhang , Yufei Xu , Jing Zhang , Bo Du , Dacheng Tao , Liangpei Zhang

While recent advances in virtual try-on (VTON) have achieved realistic garment transfer to human subjects, its inverse task, virtual try-off (VTOFF), which aims to reconstruct canonical garment templates from dressed humans, remains…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Angang Zhang , Fang Deng , Hao Chen , Zhongjian Chen , Junyan Li

Foundational models, trained on vast and diverse datasets, have demonstrated remarkable capabilities in generalizing across different domains and distributions for various zero-shot tasks. Our work addresses the challenge of retaining these…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Tom Shaked , Yuval Goldman , Oran Shayer

The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training. To apply transformers across different data modalities,…

Machine Learning · Computer Science 2024-08-20 Viet Anh Nguyen , Minh Lenhat , Khoa Nguyen , Duong Duc Hieu , Dao Huu Hung , Truong Son Hy

By using unsupervised domain adaptation (UDA), knowledge can be transferred from a label-rich source domain to a target domain that contains relevant information but lacks labels. Many existing UDA algorithms suffer from directly using raw…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Le Luo , Bingrong Xu , Qingyong Zhang , Cheng Lian , Jie Luo

Automated visual understanding of our diverse and open world demands computer vision models to generalize well with minimal customization for specific tasks, similar to human vision. Computer vision foundation models, which are trained on…

Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize.…

Computer Vision and Pattern Recognition · Computer Science 2020-08-31 Geonuk Kim , Hong-Gyu Jung , Seong-Whan Lee

The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-11 Haojie Zhang , Yongyi Su , Xun Xu , Kui Jia

Optical satellites, with their diverse band layouts and ground sampling distances, supply indispensable evidence for tasks ranging from ecosystem surveillance to emergency response. However, significant discrepancies in band composition and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Xuyang Li , Chenyu Li , Danfeng Hong