no code implementations • 15 Dec 2023 • Peizhao Li, Junfeng He, Gang Li, Rachit Bhargava, Shaolei Shen, Nachiappan Valliappan, Youwei Liang, Hongxiang Gu, Venky Ramachandran, Golnaz Farhadi, Yang Li, Kai J Kohlhoff, Vidhya Navalpakkam
Such a model would enable predicting subjective feedback such as overall satisfaction or aesthetic quality ratings, along with the underlying human attention or interaction heatmaps and viewing order, enabling designers and content-creation models to optimize their creation for human-centric improvements.
1 code implementation • 15 Dec 2023 • Youwei Liang, Junfeng He, Gang Li, Peizhao Li, Arseniy Klimovskiy, Nicholas Carolan, Jiao Sun, Jordi Pont-Tuset, Sarah Young, Feng Yang, Junjie Ke, Krishnamurthy Dj Dvijotham, Katie Collins, Yiwen Luo, Yang Li, Kai J Kohlhoff, Deepak Ramachandran, Vidhya Navalpakkam
We show that the predicted rich human feedback can be leveraged to improve image generation, for example, by selecting high-quality training data to finetune and improve the generative models, or by creating masks with predicted heatmaps to inpaint the problematic regions.
no code implementations • 16 Jun 2023 • TingWei Liu, Peizhao Li, Hongfu Liu
To address this gap, we propose a notion edge balance to measure the proportion of edges connecting different demographic groups in clusters.
no code implementations • 29 Nov 2022 • Peizhao Li, Ethan Xia, Hongfu Liu
Fairness is essential for machine learning systems deployed in high-stake applications.
no code implementations • 14 Oct 2022 • Zizhang Chen, Peizhao Li, Hongfu Liu, Pengyu Hong
To fill this gap, we started with the simple graph convolution (SGC) model that operates on an attributed graph and formulated an influence function to approximate the changes in model parameters when a node or an edge is removed from an attributed graph.
1 code implementation • 4 Oct 2022 • Anshuman Chhabra, Peizhao Li, Prasant Mohapatra, Hongfu Liu
Experimentally, we observe that CFC is highly robust to the proposed attack and is thus a truly robust fair clustering alternative.
no code implementations • CVPR 2022 • Peizhao Li, Pu Wang, Karl Berntorp, Hongfu Liu
We consider the object recognition problem in autonomous driving using automotive radar sensors.
Ranked #1 on Multiple Object Tracking on RADIATE
1 code implementation • 1 Feb 2022 • Peizhao Li, Hongfu Liu
With the fast development of algorithmic governance, fairness has become a compulsory property for machine learning models to suppress unintentional discrimination.
no code implementations • 29 Sep 2021 • Peizhao Li, Xuchao Zhang, Ziyu Yao, Wei Cheng, Haifeng Chen, Hongfu Liu
To achieve this, we propose a machine learning approach to adapt the editorial style derived from few exemplars to a query code snippet.
1 code implementation • 9 Jun 2021 • Hanyu Song, Peizhao Li, Hongfu Liu
In this paper, we focus on the fairness issues regarding unsupervised outlier detection.
no code implementations • CVPR 2021 • Peizhao Li, Jiuxiang Gu, Jason Kuen, Vlad I. Morariu, Handong Zhao, Rajiv Jain, Varun Manjunatha, Hongfu Liu
For downstream usage, we propose a novel modality-adaptive attention mechanism for multimodal feature fusion by adaptively emphasizing language and vision signals.
1 code implementation • ICLR 2021 • Peizhao Li, Yifei Wang, Han Zhao, Pengyu Hong, Hongfu Liu
Disparate impact has raised serious concerns in machine learning applications and its societal impacts.
no code implementations • 16 Jun 2020 • Peizhao Li, Zhengming Ding, Hongfu Liu
Unsupervised domain adaptation targets to transfer task-related knowledge from labeled source domain to unlabeled target domain.
1 code implementation • CVPR 2020 • Peizhao Li, Han Zhao, Hongfu Liu
In light of these limitations, in this paper, we propose Deep Fair Clustering (DFC) to learn fair and clustering-favorable representations for clustering simultaneously.
1 code implementation • 11 Jul 2019 • Xiaolong Jiang, Peizhao Li, Yanjing Li, Xian-Tong Zhen
In this work, we present an end-to-end framework to settle data association in online Multiple-Object Tracking (MOT).
no code implementations • 29 Jan 2019 • Peizhao Li, Yanjing Li, Xiao-Long Jiang, Xian-Tong Zhen
In this paper, we present a two-stream multi-task network for fashion recognition.
no code implementations • 16 Dec 2018 • Xiaolong Jiang, Peizhao Li, Xian-Tong Zhen, Xian-Bin Cao
To overcome the object-centric information scarcity, both appearance and motion features are deeply integrated by the proposed AMNet, which is an end-to-end offline trained two-stream network.