Author name cluster

Pengfei Wei

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

10 papers

1 author row

AAAI Conference 2024 Conference Paper

Prior and Prediction Inverse Kernel Transformer for Single Image Defocus Deblurring

Peng Tang
Zhiqiang Xu
Chunlai Zhou
Pengfei Wei
Peng Han
Xin Cao
Tobias Lasser

Defocus blur, due to spatially-varying sizes and shapes, is hard to remove. Existing methods either are unable to effectively handle irregular defocus blur or fail to generalize well on other datasets. In this work, we propose a divide-and-conquer approach to tackling this issue, which gives rise to a novel end-to-end deep learning method, called prior-and-prediction inverse kernel transformer (P2IKT), for single image defocus deblurring. Since most defocus blur can be approximated as Gaussian blur or its variants, we construct an inverse Gaussian kernel module in our method to enhance its generalization ability. At the same time, an inverse kernel prediction module is introduced in order to flexibly address the irregular blur that cannot be approximated by Gaussian blur. We further design a scale recurrent transformer, which estimates mixing coefficients for adaptively combining the results from the two modules and runs the scale recurrent ``coarse-to-fine" procedure for progressive defocus deblurring. Extensive experimental results demonstrate that our P2IKT outperforms previous methods in terms of PSNR on multiple defocus deblurring datasets.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Adaptive Policy Learning for Offline-to-Online Reinforcement Learning

Han Zheng
Xufang Luo
Pengfei Wei
Xuan Song
Dongsheng Li
Jing Jiang

Conventional reinforcement learning (RL) needs an environment to collect fresh data, which is impractical when online interactions are costly. Offline RL provides an alternative solution by directly learning from the previously collected dataset. However, it will yield unsatisfactory performance if the quality of the offline datasets is poor. In this paper, we consider an offline-to-online setting where the agent is first learned from the offline dataset and then trained online, and propose a framework called Adaptive Policy Learning for effectively taking advantage of offline and online data. Specifically, we explicitly consider the difference between the online and offline data and apply an adaptive update scheme accordingly, that is, a pessimistic update strategy for the offline dataset and an optimistic/greedy update scheme for the online dataset. Such a simple and effective method provides a way to mix the offline and online RL and achieve the best of both worlds. We further provide two detailed algorithms for implementing the framework through embedding value or policy-based RL algorithms into it. Finally, we conduct extensive experiments on popular continuous control tasks, and results show that our algorithm can learn the expert policy with high sample efficiency even when the quality of offline dataset is poor, e.g., random dataset.

PDF Details DOI

IJCAI Conference 2023 Conference Paper

AudioQR: Deep Neural Audio Watermarks For QR Code

Xinghua Qu
Xiang Yin
Pengfei Wei
Lu Lu
Zejun Ma

Image-based quick response (QR) code is frequently used, but creates barriers for the visual impaired people. With the goal of ``AI for good", this paper proposes the AudioQR, a barrier-free QR coding mechanism for the visually impaired population via deep neural audio watermarks. Previous audio watermarking approaches are mainly based on handcrafted pipelines, which is less secure and difficult to apply in large-scale scenarios. In contrast, AudioQR is the first comprehensive end-to-end pipeline that hides watermarks in audio imperceptibly and robustly. To achieve this, we jointly train an encoder and decoder, where the encoder is structured as a concatenation of transposed convolutions and multi-receptive field fusion modules. Moreover, we customize the decoder training with a stochastic data augmentation chain to make the watermarked audio robust towards different audio distortions, such as environment background, room impulse response when playing through the air, music surrounding, and Gaussian noise. Experiment results indicate that AudioQR can efficiently hide arbitrary information into audio without introducing significant perceptible difference. Our code is available at https: //github. com/xinghua-qu/AudioQR.

PDF Details DOI

YNIMG Journal 2023 Journal Article

Multi-objective optimization via evolutionary algorithm (MOVEA) for high-definition transcranial electrical stimulation of the human brain

Mo WANG
Kexin Lou
Zeming Liu
Pengfei Wei
Quanying Liu

Designing a transcranial electrical stimulation (tES) strategy requires considering multiple objectives, such as intensity in the target area, focality, stimulation depth, and avoidance zone. These objectives are often mutually exclusive. In this paper, we propose a general framework, called multi-objective optimization via evolutionary algorithm (MOVEA), which solves the non-convex optimization problem in designing tES strategies without a predefined direction. MOVEA enables simultaneous optimization of multiple targets through Pareto optimization, generating a Pareto front after a single run without manual weight adjustment and allowing easy expansion to more targets. This Pareto front consists of optimal solutions that meet various requirements while respecting trade-off relationships between conflicting objectives such as intensity and focality. MOVEA is versatile and suitable for both transcranial alternating current stimulation (tACS) and transcranial temporal interference stimulation (tTIS) based on high definition (HD) and two-pair systems. We comprehensively compared tACS and tTIS in terms of intensity, focality, and steerability for targets at different depths. Our findings reveal that tTIS enhances focality by reducing activated volume outside the target by 60%. HD-tTIS and HD-tDCS can achieve equivalent maximum intensities, surpassing those of two-pair tTIS, such as 0.51 V/m under HD-tACS/HD-tTIS and 0.42 V/m under two-pair tTIS for the motor area as a target. Analysis of variance in eight subjects highlights individual differences in both optimal stimulation policies and outcomes for tACS and tTIS, emphasizing the need for personalized stimulation protocols. These findings provide guidance for designing appropriate stimulation strategies for tACS and tTIS. MOVEA facilitates the optimization of tES based on specific objectives and constraints, advancing tTIS and tACS-based neuromodulation in understanding the causal relationship between brain regions and cognitive functions and treating diseases. The code for MOVEA is available at https://github.com/ncclabsustech/MOVEA.

Details DOI

NeurIPS Conference 2023 Conference Paper

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

Pengfei Wei
Lingdong Kong
Xinghua Qu
Yi Ren
Zhiqiang Xu
Jing Jiang
Xiang Yin

Unsupervised video domain adaptation is a practical yet challenging task. In this work, for the first time, we tackle it from a disentanglement view. Our key idea is to handle the spatial and temporal domain divergence separately through disentanglement. Specifically, we consider the generation of cross-domain videos from two sets of latent factors, one encoding the static information and another encoding the dynamic information. A Transfer Sequential VAE (TranSVAE) framework is then developed to model such generation. To better serve for adaptation, we propose several objectives to constrain the latent factors. With these constraints, the spatial divergence can be readily removed by disentangling the static domain-specific information out, and the temporal divergence is further reduced from both frame- and video-levels through adversarial learning. Extensive experiments on the UCF-HMDB, Jester, and Epic-Kitchens datasets verify the effectiveness and superiority of TranSVAE compared with several state-of-the-art approaches.

PDF Details

NeurIPS Conference 2020 Conference Paper

Cooperative Heterogeneous Deep Reinforcement Learning

Han Zheng
Pengfei Wei
Jing Jiang
Guodong Long
Qinghua Lu
Chengqi Zhang

Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep Reinforcement Learning (CHDRL) framework that can learn a policy by integrating the advantages of heterogeneous agents. Specifically, we propose a cooperative learning framework that classifies heterogeneous agents into two classes: global agents and local agents. Global agents are off-policy agents that can utilize experiences from the other agents. Local agents are either on-policy agents or population-based evolutionary algorithms (EAs) agents that can explore the local area effectively. We employ global agents, which are sample-efficient, to guide the learning of local agents so that local agents can benefit from the sample-efficient agents and simultaneously maintain their advantages, e. g. , stability. Global agents also benefit from effective local searches. Experimental studies on a range of continuous control tasks from the Mujoco benchmark show that CHDRL achieves better performance compared with state-of-the-art baselines.

PDF Details

PRL Workshop 2020 Workshop Paper

Hierarchical Reinforcement Learning in StarCraft II with Human Expertise in Subgoals Selection

Xinyi Xu
Tiancheng Huang
Pengfei Wei
Akshay Narayan
Tze-Yun Leong

This work is inspired by recent advances in hierarchical reinforcement learning (HRL) (Barto and Mahadevan 2003; Hengst 2010), and improvements in learning efficiency from heuristic-based subgoal selection, experience replay (Lin 1993; Andrychowicz et al. 2017), and task-based curriculum learning (Bengio et al. 2009; Zaremba and Sutskever 2014). We propose a new method to integrate HRL, experience replay and effective subgoal selection through an implicit curriculum design based on human expertise to support sample-efficient learning and enhance interpretability of the agent’s behavior. Human expertise remains indispensable in many areas such as medicine (Buch, Ahmed, and Maruthappu 2018) and law (Cath 2018), where interpretability, explainability and transparency are crucial in the decision making process, for ethical and legal reasons. Our method simplifies the complex task sets for achieving the overall objectives by decomposing them into subgoals at different levels of abstraction. Incorporating relevant subjective knowledge also significantly reduces the computational resources spent in exploration for RL, especially in high speed, changing, and complex environments where the transition dynamics cannot be effectively learned and modelled in a short time. Experimental results in two StarCraft II (SC2) (Vinyals et al. 2017) minigames demonstrate that our method can achieve better sample efficiency than flat and end-to-end RL methods, and provides an effective method for explaining the agent’s performance.

PDF Details

NeurIPS Conference 2020 Conference Paper

MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler

Zhining Liu
Pengfei Wei
Jing Jiang
Wei Cao
Jiang Bian
Yi Chang

Imbalanced learning (IL), i. e. , learning unbiased models from class-imbalanced data, is a challenging problem. Typical IL methods including resampling and reweighting were designed based on some heuristic assumptions. They often suffer from unstable performance, poor applicability, and high computational cost in complex tasks where their assumptions do not hold. In this paper, we introduce a novel ensemble IL framework named MESA. It adaptively resamples the training set in iterations to get multiple classifiers and forms a cascade ensemble model. MESA directly learns the sampling strategy from data to optimize the final metric beyond following random heuristics. Moreover, unlike prevailing meta-learning-based IL solutions, we decouple the model-training and meta-training in MESA by independently train the meta-sampler over task-agnostic meta-data. This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks. Extensive experiments on both synthetic and real-world tasks demonstrate the effectiveness, robustness, and transferability of MESA. Our code is available at https: //github. com/ZhiningLiu1998/mesa.

PDF Details

IJCAI Conference 2019 Conference Paper

Learning Disentangled Semantic Representation for Domain Adaptation

Ruichu Cai
Zijian Li
Pengfei Wei
Jie Qiao
Kun Zhang
Zhifeng Hao

Domain adaptation is an important but challenging task. Most of the existing domain adaptation methods struggle to extract the domain-invariant representation on the feature space with entangling domain information and semantic information. Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data. In DSR, we assume the data generation process is controlled by two independent sets of variables, i. e. , the semantic latent variables and the domain latent variables. Under the above assumption, we employ a variational auto-encoder to reconstruct the semantic latent variables and domain latent variables behind the data. We further devise a dual adversarial network to disentangle these two sets of reconstructed latent variables. The disentangled semantic latent variables are finally adapted across the domains. Experimental studies testify that our model yields state-of-the-art performance on several domain adaptation benchmark datasets.

PDF Details

IJCAI Conference 2016 Conference Paper

Deep Nonlinear Feature Coding for Unsupervised Domain Adaptation

Pengfei Wei
Yiping Ke
Chi Keong Goh

Deep feature learning has recently emerged with demonstrated effectiveness in domain adaptation. In this paper, we propose a Deep Nonlinear Feature Coding framework (DNFC) for unsupervised domain adaptation. DNFC builds on the marginalized stacked denoising autoencoder (mSDA) to extract rich deep features. We introduce two new elements to mSDA: domain divergence minimization by Maximum Mean Discrepancy (MMD), and nonlinear coding by kernelization. These two elements are essential for domain adaptation as they ensure the extracted deep features to have a small distribution discrepancy and encode data nonlinearity. The effectiveness of DNFC is verified by extensive experiments on benchmark datasets. Specifically, DNFC attains much higher prediction accuracy than state-of-the-art domain adaptation methods. Compared to its basis mSDA, DNFC is able to achieve remarkable prediction improvement and meanwhile converges much faster with a small number of stacked layers.

PDF Details