no code implementations • 12 Mar 2024 • Hanning Chen, Wenjun Huang, Yang Ni, Sanggeon Yun, Fei Wen, Hugo Latapie, Mohsen Imani
Nevertheless, the naive application of VLMs leads to sub-optimal quality, due to the misalignment between embeddings of object images and their visual attributes, which are mainly adjective phrases.
no code implementations • 9 Mar 2024 • Hanning Chen, Yang Ni, Ali Zakeri, Zhuowen Zou, Sanggeon Yun, Fei Wen, Behnam Khaleghi, Narayan Srinivasa, Hugo Latapie, Mohsen Imani
When conducting cross-models and cross-platforms comparison, HDReason yields an average 4. 2x higher performance and 3. 4x better energy efficiency with similar accuracy versus the state-of-the-art FPGA-based GCN training platform.
no code implementations • 24 Feb 2024 • Shuyu Yin, Qixuan Zhou, Fei Wen, Tao Luo
However, existing performance analyses ignores the unique characteristics of continuous-time control problems, is unable to directly estimate the generalization error of the Bellman optimal loss and require a boundedness assumption.
no code implementations • 29 Apr 2023 • Fei Wen, Wei Wang, Wenxian Yu
Recent studies show that, without any prior model, the unsupervised restoration learning problem can be optimally formulated as an optimal transport (OT) problem, which has shown promising performance on denoising tasks to approach the performance of supervised methods.
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.
2 code implementations • 13 Dec 2021 • Youcai Zhang, Yuhao Cheng, Xinyu Huang, Fei Wen, Rui Feng, Yaqian Li, Yandong Guo
Multi-label learning in the presence of missing labels (MLML) is a challenging problem.
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.
no code implementations • 20 Jan 2021 • Zhonghao Zhang, Yipeng Liu, Xingyu Cao, Fei Wen, Ce Zhu
In this paper, we develop a general framework named scalable deep compressive sensing (SDCS) for the scalable sampling and reconstruction (SSR) of all existing end-to-end-trained models.
1 code implementation • 15 Sep 2020 • Dongrui Liu, Chuanchuan Chen, Changqing Xu, Qi Cai, Lei Chu, Fei Wen, Robert Caiming Qiu
We prove that CAT is a rotation and translation-invariant transformation based on the theoretical analysis.
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.
no code implementations • 29 Jun 2020 • Zhen Long, Yipeng Liu, Sixing Zeng, Jiani Liu, Fei Wen, Ce Zhu
In this paper, we present a HSI restoration method named smooth and robust low rank tensor recovery.
1 code implementation • 21 Apr 2020 • Zhonghao Zhang, Yipeng Liu, Jiani Liu, Fei Wen, Ce Zhu
By unfolding the iterative optimization algorithm for model-based methods onto networks, deep unfolding methods have the good interpretation of model-based methods and the high speed of classical deep network methods.
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.
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.
no code implementations • 26 Jun 2018 • Fei Wen, You Zhang, Wei Wang
Whereafter, the normalized Laplacian spectra of $G_1^S\bowtie (G_2^V\cup G_3^E)$ and $G_1^S\diamondsuit(G_2^V\cup G_3^E)$ are respectively determined in terms of the corresponding normalized Laplacian spectra of the connected regular graphs $G_{1}$, $G_{2}$ and $G_{3}$, which extend the corresponding results of [A. Das, P. Panigrahi, Linear Multil.
Combinatorics
1 code implementation • 24 Apr 2018 • Lei Chu, Fei Wen, Lily Li, Robert Qiu
The power consumption of digital-to-analog converters (DACs) constitutes a significant proportion of the total power consumption in a massive multiuser multiple-input multiple-output (MU-MIMO) base station (BS).
Signal Processing Optimization and Control
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.