1 code implementation • 21 Sep 2022 • Xiangzuo Huo, Gang Sun, Shengwei Tian, Yan Wang, Long Yu, Jun Long, Wendong Zhang, Aolun Li
A parallel hierarchy of local and global feature blocks is designed to efficiently extract local features and global representations at various semantic scales, with the flexibility to model at different scales and linear computational complexity relevant to image size.
1 code implementation • 30 Aug 2022 • Tianyuan Yao, Chang Qu, Jun Long, Quan Liu, Ruining Deng, Yuanhan Tian, Jiachen Xu, Aadarsh Jha, Zuhayr Asad, Shunxing Bao, Mengyang Zhao, Agnes B. Fogo, Bennett A. Landman, Haichun Yang, Catie Chang, Yuankai Huo
In order to extract and separate compound figures into usable individual images for downstream learning, we propose a simple compound figure separation (SimCFS) framework without using the traditionally required detection bounding box annotations, with a new loss function and a hard case simulation.
1 code implementation • 27 Jun 2022 • Ruining Deng, Quan Liu, Can Cui, Tianyuan Yao, Jun Long, Zuhayr Asad, R. Michael Womick, Zheyu Zhu, Agnes B. Fogo, Shilin Zhao, Haichun Yang, Yuankai Huo
The contribution of this paper is three-fold: (1) a novel scale-aware controller is proposed to generalize the dynamic neural network from single-scale to multi-scale; (2) semi-supervised consistency regularization of pseudo-labels is introduced to model the inter-scale correlation of unannotated tissue types into a single end-to-end learning paradigm; and (3) superior scale-aware generalization is evidenced by directly applying a model trained on human kidney images to mouse kidney images, without retraining.
1 code implementation • 31 May 2022 • Tianyuan Yao, Yuzhe Lu, Jun Long, Aadarsh Jha, Zheyu Zhu, Zuhayr Asad, Haichun Yang, Agnes B. Fogo, Yuankai Huo
To leverage the performance of the Glo-In-One toolkit, we introduce self-supervised deep learning to glomerular quantification via large-scale web image mining.
no code implementations • 6 Jan 2021 • Fan Wang, Lei Luo, En Zhu, Siwei Wang, Jun Long
Recent Multiple Object Tracking (MOT) methods have gradually attempted to integrate object detection and instance re-identification (Re-ID) into a united network to form a one-stage solution.
no code implementations • 29 Mar 2019 • Zhan Yang, Osolo Ian Raymond, Wuqing Sun, Jun Long
However, we argue that the current deep learning based hashing methods ignore some critical problems (e. g., the learned hash codes are not discriminative due to the hashing methods being unable to discover rich semantic information and the training strategy having difficulty optimizing the discrete binary codes).
no code implementations • 13 Mar 2019 • Jun Long, WuQing Sun, Zhan Yang, Osolo Ian Raymond
Human Activity Recognition (HAR) using deep neural network has become a hot topic in human-computer interaction.
no code implementations • 4 Dec 2018 • Zhan Yang, Osolo Ian Raymond, Wuqing Sun, Jun Long
The core idea is to use guided hash codes which are generated by the hashing network of the first stream framework (called first hashing network) to guide the training of the hashing network of the second stream framework (called second hashing network).
no code implementations • 31 Jul 2018 • Kamal Al-Sabahi, Zuping Zhang, Jun Long, Khaled Alwesabi
To ensure the effectiveness of the proposed LSA-based sentence selection algorithm, extensive experiment on Arabic and English are done.
no code implementations • 31 Jul 2018 • Zhan Yang, Osolo Ian Raymond, ChengYuan Zhang, Ying Wan, Jun Long
Using the quantization method proposed, we were able to achieve performances closer to that of full-precision counterpart.