Search Results for author: Juhua Hu

Found 18 papers, 12 papers with code

Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning

1 code implementation6 Nov 2024 Jiawei Yao, Qi Qian, Juhua Hu

Multiple clustering aims to discover various latent structures of data from different aspects.

Clustering

SimInversion: A Simple Framework for Inversion-Based Text-to-Image Editing

no code implementations16 Sep 2024 Qi Qian, Haiyang Xu, Ming Yan, Juhua Hu

Diffusion models demonstrate impressive image generation performance with text guidance.

Image Generation

Text-Guided Mixup Towards Long-Tailed Image Categorization

1 code implementation5 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.

Ensemble Learning Few-Shot Learning +1

SeA: Semantic Adversarial Augmentation for Last Layer Features from Unsupervised Representation Learning

1 code implementation23 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.

Representation Learning

Online Zero-Shot Classification with CLIP

1 code implementation23 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.

Classification Zero-Shot Learning

Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering

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.

Clustering

Dual-disentangled Deep Multiple Clustering

1 code implementation7 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.

Clustering Disentanglement

AugDMC: Data Augmentation Guided Deep Multiple Clustering

1 code implementation22 Jun 2023 Jiawei Yao, Enbei Liu, Maham Rashid, Juhua Hu

Thereafter, multiple clusterings based on different aspects of the data can be obtained.

Clustering Data Augmentation +2

NPRL: Nightly Profile Representation Learning for Early Sepsis Onset Prediction in ICU Trauma Patients

no code implementations25 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).

Representation Learning

Multi-Subset Approach to Early Sepsis Prediction

no code implementations13 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.

Prediction

Improved Visual Fine-tuning with Natural Language Supervision

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.

Enhancing Peak Network Traffic Prediction via Time-Series Decomposition

no code implementations9 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.

Prediction Time Series +1

Improved Knowledge Distillation via Full Kernel Matrix Transfer

1 code implementation30 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.

Knowledge Distillation Model Compression

Weakly Supervised Representation Learning with Coarse Labels

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.

Deep Learning Learning with coarse labels +1

Hierarchically Robust Representation Learning

no code implementations CVPR 2020 Qi Qian, Juhua Hu, Hao Li

Experiments on benchmark data sets demonstrate the effectiveness of the robust deep representations.

Representation Learning

Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution

no code implementations17 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.