Search Results for author: Jun-Jie Zhang

Found 15 papers, 3 papers with code

On the uncertainty principle of neural networks

no code implementations3 May 2022 Jun-Jie Zhang, Dong-Xiao Zhang, Jian-Nan Chen, Long-Gang Pang

Here, we show that the accuracy-robustness trade-off is an intrinsic property whose underlying mechanism is deeply related to the uncertainty principle in quantum mechanics.

DSP: A Differential Spatial Prediction Scheme for Comprehensive real industrial datasets

no code implementations23 Aug 2020 Jun-Jie Zhang, Cong Zhang, Neal N. Xiong

The improved deep reinforcement learning network is then used to search for and learn the hyperparameters of each sample point in the inverse distance weighted model.

reinforcement-learning

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples

no code implementations28 May 2020 Huaxi Huang, Jun-Jie Zhang, Jian Zhang, Qiang Wu, Chang Xu

The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i. e.,} Fine-Grained categorization problems under the Few-Shot setting (FGFS).

Fine-Grained Visual Categorization

CFR-RL: Traffic Engineering with Reinforcement Learning in SDN

2 code implementations24 Apr 2020 Jun-Jie Zhang, Minghao Ye, Zehua Guo, Chen-Yu Yen, H. Jonathan Chao

In this paper, we propose CFR-RL (Critical Flow Rerouting-Reinforcement Learning), a Reinforcement Learning-based scheme that learns a policy to select critical flows for each given traffic matrix automatically.

reinforcement-learning

To Balance or Not to Balance: A Simple-yet-Effective Approach for Learning with Long-Tailed Distributions

no code implementations10 Dec 2019 Jun-Jie Zhang, Lingqiao Liu, Peng Wang, Chunhua Shen

Such imbalanced distribution causes a great challenge for learning a deep neural network, which can be boiled down into a dilemma: on the one hand, we prefer to increase the exposure of tail class samples to avoid the excessive dominance of head classes in the classifier training.

Auxiliary Learning Self-Supervised Learning

ZMCintegral-v5: Support for Integrations with the Scanning of Large Parameter Grids on Multi-GPUs

1 code implementation4 Oct 2019 Jun-Jie Zhang, Hong-Zhong Wu

In this updated vesion of ZMCintegral, we have added the functionality of integrations with parameter scan on distributed Graphics Processing Units(GPUs).

Computational Physics

Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification

no code implementations4 Aug 2019 Huaxi Huang, Jun-Jie Zhang, Jian Zhang, Jingsong Xu, Qiang Wu

A novel low-rank pairwise bilinear pooling operation is proposed to capture the nuanced differences between the support and query images for learning an effective distance metric.

Classification Few-Shot Learning +2

Mind Your Neighbours: Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks

no code implementations CVPR 2019 Jun-Jie Zhang, Qi Wu, Jian Zhang, Chunhua Shen, Jianfeng Lu

In this paper, we propose a Metadata Neighbourhood Graph Co-Attention Network (MangoNet) to model the correlations between each target image and its neighbours.

Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning

no code implementations7 Apr 2019 Huaxi Huang, Jun-Jie Zhang, Jian Zhang, Qiang Wu, Jingsong Xu

Unlike traditional deep bilinear networks for fine-grained classification, which adopt the self-bilinear pooling to capture the subtle features of images, the proposed model uses a novel pairwise bilinear pooling to compare the nuanced differences between base images and query images for learning a deep distance metric.

General Classification Meta-Learning

A Package for Multi-Dimensional Monte Carlo Integration on Multi-GPUs

1 code implementation21 Feb 2019 Hong-Zhong Wu, Jun-Jie Zhang, Long-Gang Pang, Qun Wang

We have demonstrated that Tensorflow and Numba help inexperienced scientific researchers to parallelize their programs on multiple GPUs with little work.

Computational Physics

Goal-Oriented Visual Question Generation via Intermediate Rewards

no code implementations ECCV 2018 Jun-Jie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu, Anton Van Den Hengel

Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.

Informativeness Question Generation +1

A Pulmonary Nodule Detection Model Based on Progressive Resolution and Hierarchical Saliency

no code implementations2 Jul 2018 Jun-Jie Zhang, Yong Xia, Yanning Zhang

Detection of pulmonary nodules on chest CT is an essential step in the early diagnosis of lung cancer, which is critical for best patient care.

Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards

no code implementations21 Nov 2017 Jun-Jie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu, Anton Van Den Hengel

Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge.

Informativeness Question Generation +1

Kill Two Birds with One Stone: Weakly-Supervised Neural Network for Image Annotation and Tag Refinement

no code implementations19 Nov 2017 Jun-Jie Zhang, Qi Wu, Jian Zhang, Chunhua Shen, Jianfeng Lu

These comments can be a description of the image, or some objects, attributes, scenes in it, which are normally used as the user-provided tags.

TAG

Multi-Label Image Classification with Regional Latent Semantic Dependencies

no code implementations4 Dec 2016 Jun-Jie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu

Recent state-of-the-art approaches to multi-label image classification exploit the label dependencies in an image, at global level, largely improving the labeling capacity.

Classification General Classification +1

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