Search Results for author: Faen Zhang

Found 14 papers, 6 papers with code

Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels

no code implementations18 Nov 2023 Shu-Lin Xu, Yifan Sun, Faen Zhang, Anqi Xu, Xiu-Shen Wei, Yi Yang

Learning fine-grained embeddings from coarse labels is a challenging task due to limited label granularity supervision, i. e., lacking the detailed distinctions required for fine-grained tasks.

Watch out Venomous Snake Species: A Solution to SnakeCLEF2023

1 code implementation19 Jul 2023 Feiran Hu, Peng Wang, Yangyang Li, Chenlong Duan, Zijian Zhu, Fei Wang, Faen Zhang, Yong Li, Xiu-Shen Wei

The SnakeCLEF2023 competition aims to the development of advanced algorithms for snake species identification through the analysis of images and accompanying metadata.

Data Augmentation

Delving Deep into Simplicity Bias for Long-Tailed Image Recognition

no code implementations7 Feb 2023 Xiu-Shen Wei, Xuhao Sun, Yang shen, Anqi Xu, Peng Wang, Faen Zhang

Simplicity Bias (SB) is a phenomenon that deep neural networks tend to rely favorably on simpler predictive patterns but ignore some complex features when applied to supervised discriminative tasks.

Long-tail Learning Self-Supervised Learning

Automatic Check-Out via Prototype-based Classifier Learning from Single-Product Exemplars

4 code implementations The European Conference on Computer Vision (ECCV) 2022 Hao Chen, Xiu-Shen Wei, Faen Zhang, Yang shen, Hui Xu, Liang Xiao

Automatic Check-Out (ACO) aims to accurately predict the presence and count of each category of products in check-out images, where a major challenge is the significant domain gap between training data (single-product exemplars) and test data (check-out images).


An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning

3 code implementations28 Sep 2022 Xiu-Shen Wei, He-Yang Xu, Faen Zhang, Yuxin Peng, Wei Zhou

Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data.

Few-Shot Learning

Dual Attention Networks for Few-Shot Fine-Grained Recognition

3 code implementations Proceedings of the AAAI Conference on Artificial Intelligence 2022 Shu-Lin Xu, Faen Zhang, Xiu-Shen Wei, Jianhua Wang

Specifically, by producing attention guidance from deep activations of input images, our hard-attention is realized by keeping a few useful deep descriptors and forming them as a bag of multi-instance learning.

Hard Attention Meta-Learning

Monotonic Neural Network: combining Deep Learning with Domain Knowledge for Chiller Plants Energy Optimization

no code implementations11 Jun 2021 Fanhe Ma, Faen Zhang, Shenglan Ben, Shuxin Qin, Pengcheng Zhou, Changsheng Zhou, Fengyi Xu

In this paper, we are interested in building a domain knowledge based deep learning framework to solve the chiller plants energy optimization problems.

Image Classification

Zero-Shot Instance Segmentation

4 code implementations CVPR 2021 Ye Zheng, JiaHong Wu, Yongqiang Qin, Faen Zhang, Li Cui

We follow this motivation and propose a new task set named zero-shot instance segmentation (ZSI).

Instance Segmentation object-detection +3

Regression via Arbitrary Quantile Modeling

1 code implementation13 Nov 2019 Faen Zhang, Xinyu Fan, Hui Xu, Pengcheng Zhou, Yujian He, Junlong Liu

In the regression problem, L1 and L2 are the most commonly used loss functions, which produce mean predictions with different biases.


HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking

no code implementations31 Aug 2019 Shen Yan, Biyi Fang, Faen Zhang, Yu Zheng, Xiao Zeng, Hui Xu, Mi Zhang

Without the constraint imposed by the hand-designed heuristics, our searched networks contain more flexible and meaningful architectures that existing weight sharing based NAS approaches are not able to discover.

Neural Architecture Search

Accurate Face Detection for High Performance

no code implementations5 May 2019 Faen Zhang, Xinyu Fan, Guo Ai, Jianfei Song, Yongqiang Qin, Jia-Hong Wu

Face detection has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs).

Data Augmentation Face Detection +5

Deep Residual Networks with a Fully Connected Recon-struction Layer for Single Image Super-Resolution

no code implementations24 May 2018 Yongliang Tang, Jiashui Huang, Faen Zhang, Weiguo Gong

Recently, deep neural networks have achieved impressive performance in terms of both reconstruction accuracy and efficiency for single image super-resolution (SISR).

Image Super-Resolution

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