b'Zhenguo Li'

Unsupervised Pretraining for Object Detection by Patch Reidentification

Unsupervised representation learning achieves promising performances in ...
03/08/2021 ∙ by Jian Ding, et al. ∙ 0 ∙ share

read it
SparseBERT: Rethinking the Importance Analysis in Self-attention

Transformer-based models are popular for natural language processing (NL...
02/25/2021 ∙ by Han Shi, et al. ∙ 0 ∙ share

read it
DetCo: Unsupervised Contrastive Learning for Object Detection

Unsupervised contrastive learning achieves great success in learning ima...
02/09/2021 ∙ by Enze Xie, et al. ∙ 16 ∙ share

read it
Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search

Designing proper loss functions for vision tasks has been a long-standin...
02/09/2021 ∙ by Peidong Liu, et al. ∙ 0 ∙ share

read it
Out-of-Distribution Generalization Analysis via Influence Function

The mismatch between training and target data is one major challenge for...
01/21/2021 ∙ by Haotian Ye, et al. ∙ 6 ∙ share

read it
Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptation

Semi-supervised domain adaptation (SSDA), which aims to learn models in ...
01/05/2021 ∙ by Qijun Luo, et al. ∙ 10 ∙ share

read it
ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning

Continual learning usually assumes the incoming data are fully labeled, ...
01/02/2021 ∙ by Liyuan Wang, et al. ∙ 6 ∙ share

read it
MetaAugment: Sample-Aware Data Augmentation Policy Learning

Automated data augmentation has shown superior performance in image reco...
12/22/2020 ∙ by Fengwei Zhou, et al. ∙ 1 ∙ share

read it
DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation

While deep learning demonstrates its strong ability to handle independen...
12/17/2020 ∙ by Haoyue Bai, et al. ∙ 0 ∙ share

read it
AutoDis: Automatic Discretization for Embedding Numerical Features in CTR Prediction

Learning sophisticated feature interactions is crucial for Click-Through...
12/16/2020 ∙ by Huifeng Guo, et al. ∙ 0 ∙ share

read it
Batch Group Normalization

Deep Convolutional Neural Networks (DCNNs) are hard and time-consuming t...
12/04/2020 ∙ by Xiao-Yun Zhou, et al. ∙ 0 ∙ share

read it
MOFA: Modular Factorial Design for Hyperparameter Optimization

Automated hyperparameter optimization (HPO) has shown great power in man...
11/18/2020 ∙ by Bo Xiong, et al. ∙ 0 ∙ share

read it
Penalty and Augmented Lagrangian Methods for Layer-parallel Training of Residual Networks

Algorithms for training residual networks (ResNets) typically require fo...
09/03/2020 ∙ by Qi Sun, et al. ∙ 0 ∙ share

read it
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending

We address the curve lane detection problem which poses more realistic c...
07/23/2020 ∙ by Hang Xu, et al. ∙ 6 ∙ share

read it
AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling

Most state-of-the-art object detection systems follow an anchor-based di...
07/18/2020 ∙ by Wenshuo Ma, et al. ∙ 0 ∙ share

read it
An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization

The evaluation of hyperparameters, neural architectures, or data augment...
07/11/2020 ∙ by Yimin Huang, et al. ∙ 0 ∙ share

read it
Decoder-free Robustness Disentanglement without (Additional) Supervision

Adversarial Training (AT) is proposed to alleviate the adversarial vulne...
07/02/2020 ∙ by Yifei Wang, et al. ∙ 0 ∙ share

read it
New Interpretations of Normalization Methods in Deep Learning

In recent years, a variety of normalization methods have been proposed t...
06/16/2020 ∙ by Jiacheng Sun, et al. ∙ 0 ∙ share

read it
Risk Variance Penalization: From Distributional Robustness to Causality

Learning under multi-environments often requires the ability of out-of-d...
06/13/2020 ∙ by Chuanlong Xie, et al. ∙ 0 ∙ share

read it
Locally Differentially Private (Contextual) Bandits Learning

We study locally differentially private (LDP) bandits learning in this p...
06/01/2020 ∙ by Kai Zheng, et al. ∙ 4 ∙ share

read it
Boosting Few-Shot Learning With Adaptive Margin Loss

Few-shot learning (FSL) has attracted increasing attention in recent yea...
05/28/2020 ∙ by Aoxue Li, et al. ∙ 5 ∙ share

read it
Rethinking Performance Estimation in Neural Architecture Search

Neural architecture search (NAS) remains a challenging problem, which is...
05/20/2020 ∙ by Xiawu Zheng, et al. ∙ 0 ∙ share

read it
AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction

Learning effective feature interactions is crucial for click-through rat...
03/25/2020 ∙ by Bin Liu, et al. ∙ 2 ∙ share

read it
EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement

Object detectors trained on fully-annotated data currently yield state o...
02/18/2020 ∙ by Linpu Fang, et al. ∙ 0 ∙ share

read it
Universal-RCNN: Universal Object Detector via Transferable Graph R-CNN

The dominant object detection approaches treat each dataset separately a...
02/18/2020 ∙ by Hang Xu, et al. ∙ 23 ∙ share

read it
Multi-objective Neural Architecture Search via Non-stationary Policy Gradient

Multi-objective Neural Architecture Search (NAS) aims to discover novel ...
01/23/2020 ∙ by Zewei Chen, et al. ∙ 0 ∙ share

read it
MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection

Recommender systems often face heterogeneous datasets containing highly ...
01/22/2020 ∙ by Mi Luo, et al. ∙ 0 ∙ share

read it
SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

The state-of-the-art object detection method is complicated with various...
11/22/2019 ∙ by Lewei Yao, et al. ∙ 39 ∙ share

read it
DARTS+: Improved Differentiable Architecture Search with Early Stopping

Recently, there has been a growing interest in automating the process of...
09/13/2019 ∙ by Hanwen Liang, et al. ∙ 0 ∙ share

read it
Meta Reinforcement Learning with Task Embedding and Shared Policy

Despite significant progress, deep reinforcement learning (RL) suffers f...
05/16/2019 ∙ by Lin Lan, et al. ∙ 0 ∙ share

read it
Meta-Learning for Few-shot Camera-Adaptive Color Constancy

Digital camera pipelines employ color constancy methods to estimate an u...
11/28/2018 ∙ by Steven McDonagh, et al. ∙ 0 ∙ share

read it
DeepFM: An End-to-End Wide & Deep Learning Framework for CTR Prediction

Learning sophisticated feature interactions behind user behaviors is cri...
04/12/2018 ∙ by Huifeng Guo, et al. ∙ 0 ∙ share

read it
Federated Meta-Learning for Recommendation

Recommender systems have been widely studied from the machine learning p...
02/22/2018 ∙ by Fei Chen, et al. ∙ 0 ∙ share

read it
Deep Meta-Learning: Learning to Learn in the Concept Space

Few-shot learning remains challenging for meta-learning that learns a le...
02/10/2018 ∙ by Fengwei Zhou, et al. ∙ 0 ∙ share

read it
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

Learning sophisticated feature interactions behind user behaviors is cri...
03/13/2017 ∙ by Huifeng Guo, et al. ∙ 0 ∙ share

read it

Zhenguo Li

Featured Co-authors