no code implementations • 6 Feb 2024 • Ningyuan Tang, Minghao Fu, Ke Zhu, Jianxin Wu
Because learnable parameters from these methods are entangled with the pretrained model, gradients related to the frozen pretrained model's parameters have to be computed and stored during finetuning.
no code implementations • 29 Jan 2024 • Ke Zhu, Minghao Fu, Jie Shao, Tianyu Liu, Jianxin Wu
While existing methods fail to handle the regression bias, the class-specific regression head for rare classes is hypothesized to be the main cause of it in this paper.
1 code implementation • 13 Dec 2023 • Minghao Fu, Ke Zhu, Jianxin Wu
When pre-trained models become rapidly larger, the cost of fine-tuning on downstream tasks steadily increases, too.
no code implementations • ICCV 2023 • Ke Zhu, Minghao Fu, Jianxin Wu
Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module.
no code implementations • 4 Jun 2023 • Minghao Fu, Xin Man, Yihan Xu, Jie Shao
While scene text image super-resolution (STISR) has yielded remarkable improvements in accurately recognizing scene text, prior methodologies have placed excessive emphasis on optimizing performance, rather than paying due attention to efficiency - a crucial factor in ensuring deployment of the STISR-STR pipeline.
no code implementations • 27 May 2023 • Minghao Fu, Ke Zhu, Jianxin Wu
With both the new pFSL setting and novel IbM2 method, this paper shows that practical few-shot learning is both viable and promising.
1 code implementation • 13 Mar 2022 • Minghao Fu, Yun-Hao Cao, Jianxin Wu
Few-shot recognition learns a recognition model with very few (e. g., 1 or 5) images per category, and current few-shot learning methods focus on improving the average accuracy over many episodes.
no code implementations • 5 Apr 2020 • Minghao Fu, Zhenshan Xie, Wen Li, Lixin Duan
Cross-domain object detection has recently attracted more and more attention for real-world applications, since it helps build robust detectors adapting well to new environments.