no code implementations • 9 Apr 2024 • Pengfei Zhou, Fangxiang Feng, Xiaojie Wang
To deal with these issues, in this paper, we first adapt a pre-trained latent diffusion model to the image harmonization task to generate the harmonious but potentially blurry initial images.
1 code implementation • 14 Feb 2024 • Pengfei Zhou, Weiqing Min, Jiajun Song, Yang Zhang, Shuqiang Jiang
The complexity of food semantic attributes further makes it more difficult for current ZSD methods to distinguish various food categories.
no code implementations • 25 Jan 2024 • Zheqi He, Xinya Wu, Pengfei Zhou, Richeng Xuan, Guang Liu, Xi Yang, Qiannan Zhu, Hua Huang
Current multi-modal benchmarks for domain-specific knowledge concentrate on multiple-choice questions and are predominantly available in English, which imposes limitations on the comprehensiveness of the evaluation.
1 code implementation • 7 Oct 2023 • Pengfei Zhou, Weiqing Min, Yang Zhang, Jiajun Song, Ying Jin, Shuqiang Jiang
To tackle this, we propose the Semantic Separable Diffusion Synthesizer (SeeDS) framework for Zero-Shot Food Detection (ZSFD).
Ranked #1 on Generalized Zero-Shot Object Detection on MS-COCO
1 code implementation • 23 Feb 2022 • Kaining Ying, Zhenhua Wang, Cong Bai, Pengfei Zhou
Most instance segmentation models are not end-to-end trainable due to either the incorporation of proposal estimation (RPN) as a pre-processing or non-maximum suppression (NMS) as a post-processing.
Ranked #17 on Instance Segmentation on COCO test-dev (APL metric)
no code implementations • 10 May 2021 • Sujie Li, Feng Pan, Pengfei Zhou, Pan Zhang
Using numerical experiments, we demonstrate that the proposed algorithm is much more accurate than the state-of-the-art machine learning methods in estimating the partition function of restricted Boltzmann machines and deep Boltzmann machines, and have potential applications in training deep Boltzmann machines for general machine learning tasks.
1 code implementation • 16 Feb 2021 • Jie Zhang, Pengfei Zhou, Hongyan Wu
In this study, we develop a novel method, Dynamic Virtual Graph Significance Networks (DVGSN), which can supervisedly and dynamically learn from similar "infection situations" in historical timepoints.
1 code implementation • 6 Dec 2019 • Feng Pan, Pengfei Zhou, Sujie Li, Pan Zhang
We present a general method for approximately contracting tensor networks with an arbitrary connectivity.
Computational Physics Statistical Mechanics Strongly Correlated Electrons Quantum Physics
no code implementations • 1 Nov 2019 • Pengfei Zhou, Tianyi Li, Pan Zhang
For the first time, well-controlled benchmark datasets with asymptotially exact properties and optimal solutions could be produced for the evaluation of graph convolution neural networks, and for the theoretical understanding of their strengths and weaknesses.
no code implementations • 26 Jun 2019 • Feng Pan, Pengfei Zhou, Hai-Jun Zhou, Pan Zhang
We propose a method for solving statistical mechanics problems defined on sparse graphs.