1 code implementation • 6 Nov 2024 • Jiawei Yao, Qi Qian, Juhua Hu
Multiple clustering aims to discover various latent structures of data from different aspects.
no code implementations • 16 Sep 2024 • Qi Qian, Haiyang Xu, Ming Yan, Juhua Hu
Diffusion models demonstrate impressive image generation performance with text guidance.
1 code implementation • 5 Sep 2024 • Richard Franklin, Jiawei Yao, Deyang Zhong, Qi Qian, Juhua Hu
In many real-world applications, the frequency distribution of class labels for training data can exhibit a long-tailed distribution, which challenges traditional approaches of training deep neural networks that require heavy amounts of balanced data.
1 code implementation • 23 Aug 2024 • Qi Qian, Yuanhong Xu, Juhua Hu
To unleash the potential of fixed deep features, we propose a novel semantic adversarial augmentation (SeA) in the feature space for optimization.
1 code implementation • 23 Aug 2024 • Qi Qian, Juhua Hu
While CLIP demonstrates an impressive zero-shot performance on diverse downstream tasks, the distribution from the target data has not been leveraged sufficiently.
1 code implementation • CVPR 2024 • Jiawei Yao, Qi Qian, Juhua Hu
Traditionally, aligning a user's brief keyword of interest with the corresponding vision components was challenging, but the emergence of multi-modal and large language models (LLMs) has begun to bridge this gap.
1 code implementation • 7 Feb 2024 • Jiawei Yao, Juhua Hu
In the E-step, the disentanglement learning module employs coarse-grained and fine-grained disentangled representations to obtain a more diverse set of latent factors from the data.
1 code implementation • 22 Jun 2023 • Jiawei Yao, Enbei Liu, Maham Rashid, Juhua Hu
Thereafter, multiple clusterings based on different aspects of the data can be obtained.
no code implementations • 25 Apr 2023 • Tucker Stewart, Katherine Stern, Grant O'Keefe, Ankur Teredesai, Juhua Hu
Recently, deep learning methodologies have been proposed to predict sepsis, but some fail to capture the time of onset (e. g., classifying patients' entire visits as developing sepsis or not) and others are unrealistic for deployment in clinical settings (e. g., creating training instances using a fixed time to onset, where the time of onset needs to be known apriori).
no code implementations • 13 Apr 2023 • Kevin Ewig, Xiangwen Lin, Tucker Stewart, Katherine Stern, Grant O'Keefe, Ankur Teredesai, Juhua Hu
However, clinical scores like Sequential Organ Failure Assessment (SOFA) are not applicable for early prediction, while machine learning algorithms can help capture the progressing pattern for early prediction.
1 code implementation • ICCV 2023 • Junyang Wang, Yuanhong Xu, Juhua Hu, Ming Yan, Jitao Sang, Qi Qian
Fine-tuning a visual pre-trained model can leverage the semantic information from large-scale pre-training data and mitigate the over-fitting problem on downstream vision tasks with limited training examples.
no code implementations • 9 Mar 2023 • Tucker Stewart, Bin Yu, Anderson Nascimento, Juhua Hu
For network administration and maintenance, it is critical to anticipate when networks will receive peak volumes of traffic so that adequate resources can be allocated to service requests made to servers.
1 code implementation • CVPR 2022 • Qi Qian, Yuanhong Xu, Juhua Hu, Hao Li, Rong Jin
Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination.
Ranked #6 on
Unsupervised Image Classification
on CIFAR-10
1 code implementation • 30 Sep 2020 • Qi Qian, Hao Li, Juhua Hu
Recently, a number of works propose to transfer the pairwise similarity between examples to distill relative information.
1 code implementation • ICCV 2021 • Yuanhong Xu, Qi Qian, Hao Li, Rong Jin, Juhua Hu
To mitigate this challenge, we propose an algorithm to learn the fine-grained patterns for the target task, when only its coarse-class labels are available.
no code implementations • CVPR 2020 • Qi Qian, Juhua Hu, Hao Li
Experiments on benchmark data sets demonstrate the effectiveness of the robust deep representations.
5 code implementations • ICCV 2019 • Qi Qian, Lei Shang, Baigui Sun, Juhua Hu, Hao Li, Rong Jin
The set of triplet constraints has to be sampled within the mini-batch.
Ranked #21 on
Metric Learning
on CUB-200-2011
(using extra training data)
no code implementations • 17 Feb 2018 • Lingyang Chu, Xia Hu, Juhua Hu, Lanjun Wang, Jian Pei
Strong intelligent machines powered by deep neural networks are increasingly deployed as black boxes to make decisions in risk-sensitive domains, such as finance and medical.