no code implementations • 7 Sep 2024 • Lele Chang, Peilin Liu, Qinghai Guo, Fei Wen
This work shows that, based on the invariance property of MI, explicit MI maximization can be applied to SSL under a generic distribution assumption, i. e., a relaxed condition of the data distribution.
no code implementations • 3 Sep 2024 • Dexin Duan, Peilin Liu, Fei Wen
Besides, we propose an adaptive activation scaling scheme to boost online SNN adaptation performance, particularly in low time-steps.
no code implementations • 18 Jul 2024 • Shuyu Yin, Fei Wen, Peilin Liu, Tao Luo
In deep reinforcement learning applications, maximizing discounted reward is often employed instead of maximizing total reward to ensure the convergence and stability of algorithms, even though the performance metric for evaluating the policy remains the total reward.
1 code implementation • 12 Jul 2024 • Yang Ma, Dongang Wang, Peilin Liu, Lynette Masters, Michael Barnett, Weidong Cai, Chenyu Wang
The heterogeneity of neurological conditions, ranging from structural anomalies to functional impairments, presents a significant challenge in medical imaging analysis tasks.
1 code implementation • 12 Jun 2024 • Shuyu Yin, Fei Wen, Peilin Liu, Tao Luo
Semi-gradient Q-learning is applied in many fields, but due to the absence of an explicit loss function, studying its dynamics and implicit bias in the parameter space is challenging.
1 code implementation • 3 Jun 2024 • Boxi Cao, Keming Lu, Xinyu Lu, Jiawei Chen, Mengjie Ren, Hao Xiang, Peilin Liu, Yaojie Lu, Ben He, Xianpei Han, Le Sun, Hongyu Lin, Bowen Yu
Alignment is the most critical step in building large language models (LLMs) that meet human needs.
no code implementations • 4 Apr 2024 • Dongang Wang, Peilin Liu, Hengrui Wang, Heidi Beadnall, Kain Kyle, Linda Ly, Mariano Cabezas, Geng Zhan, Ryan Sullivan, Weidong Cai, Wanli Ouyang, Fernando Calamante, Michael Barnett, Chenyu Wang
This paper focuses on an early stage phase of deep learning research, prior to model development, and proposes a strategic framework for estimating the amount of annotated data required to train patch-based segmentation networks.
no code implementations • 19 Jul 2023 • Peilin Liu, Yanni Tang, Mingyue Zhang, Wu Chen
Graph-federated learning is mainly based on the classical federated learning framework i. e., the Client-Server framework.
no code implementations • 8 May 2023 • Ning Bian, Hongyu Lin, Peilin Liu, Yaojie Lu, Chunkang Zhang, Ben He, Xianpei Han, Le Sun
LLMs, as AI agents, can observe external information, which shapes their cognition and behaviors.
1 code implementation • 11 Apr 2023 • Xingwu Ji, Peilin Liu, Haochen Niu, Xiang Chen, Rendong Ying, Fei Wen
Then, we propose a graph matching approach to select correspondence objects based on the structure layout and semantic property similarity of vertices' neighbors.
1 code implementation • 21 Jun 2022 • Zeyu Yan, Fei Wen, Peilin Liu
We prove that arbitrary points of the D-P tradeoff bound can be achieved by a simple linear interpolation between the outputs of a minimum MSE decoder and a specifically constructed perfect perceptual decoder.
no code implementations • 25 May 2022 • Shuyu Yin, Tao Luo, Peilin Liu, Zhi-Qin John Xu
In this work, we perform extensive experiments to show that TD outperforms RG, that is, when the training leads to a small Bellman residual error, the solution found by TD has a better policy and is more robust against the perturbation of neural network parameters.
no code implementations • 23 Feb 2022 • Xiaoguang Zhu, Ye Zhu, Haoyu Wang, Honglin Wen, Yan Yan, Peilin Liu
To solve the problem, we propose a multi-modality feature fusion network to combine the modalities of the skeleton sequence and RGB frame instead of the RGB video, as the key information contained by the combination of skeleton sequence and RGB frame is close to that of the skeleton sequence and RGB video.
1 code implementation • 23 Sep 2021 • Liangchen Zhou, Wenbin Jiang, Jingyan Xu, Fei Wen, Peilin Liu
Typically, a single T-F mask is first estimated based on DNN and then used to mask the spectrogram of noisy speech in an order to suppress the noise.
1 code implementation • 4 Aug 2021 • Wei Wang, Fei Wen, Zeyu Yan, Peilin Liu
Toward answering this question, this work proposes a criterion for unsupervised denoising learning based on the optimal transport theory.
1 code implementation • 5 Jun 2021 • Zeyu Yan, Fei Wen, Rendong Ying, Chao Ma, Peilin Liu
This paper provides nontrivial results theoretically revealing that, \textit{1}) the cost of achieving perfect perception quality is exactly a doubling of the lowest achievable MSE distortion, \textit{2}) an optimal encoder for the "classic" rate-distortion problem is also optimal for the perceptual compression problem, \textit{3}) distortion loss is unnecessary for training a perceptual decoder.
1 code implementation • 4 Aug 2020 • Fei Wen, Hewen Wei, Yipeng Liu, Peilin Liu
Furthermore, the new algorithms are applied to various 2D/3D registration problems.
1 code implementation • 2 Mar 2019 • Fei Wen, Rendong Ying, Peilin Liu, Trieu-Kien Truong
Besides the convergence to a stationary point for a generalized nonconvex penalty, we provide more deep analysis on a popular and important class of nonconvex penalties which have discontinuous thresholding functions.
no code implementations • 15 Dec 2018 • Guanghua Pan, Jun Wang, Rendong Ying, Peilin Liu
Deep learning on point clouds has made a lot of progress recently.
1 code implementation • 16 Aug 2018 • Fei Wen, Lei Chu, Peilin Liu, Robert C. Qiu
In recent, nonconvex regularization based sparse and low-rank recovery is of considerable interest and it in fact is a main driver of the recent progress in nonconvex and nonsmooth optimization.
1 code implementation • 9 Aug 2018 • Fei Wen, Danping Zou, Rendong Ying, Peilin Liu
This work addresses the outlier removal problem in large-scale global structure-from-motion.
1 code implementation • 15 Apr 2016 • Fei Wen, Yuan Yang, Peilin Liu, Robert C. Qiu
Further, the statistical properties of the new estimators have been analyzed for generalized nonconvex penalties.