AIConfPaper
← Search

Gang Fu

17 accepted papers

2025

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation

Michal Lukasik, Lin Chen, Harikrishna Narasimhan, Aditya Krishna Menon, Wittawat Jitkrittum, Felix X. Yu +4
ICML 2025poster

Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal area under the ROC curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How…

Cited by 1Source ↗PDF ↗Scholar ↗
2025

DeepCrossAttention: Supercharging Transformer Residual Connections

Mike Heddes, Adel Javanmard, Kyriakos Axiotis, Gang Fu, Mohammadhossein Bateni, Vahab Mirrokni
ICML 2025poster

Transformer networks have achieved remarkable success across diverse domains, leveraging a variety of architectural innovations, including residual connections. However, traditional residual connections, which simply sum the outputs of previous layers, can dilute crucial information. This work intro…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Hierarchical Adaptive Filtering Network for Text Image Specular Highlight Removal

Zhi Jiang, Jingbo Hu, Ling Zhang, Gang Fu, Chunxia Xiao
CVPR 2025poster

Despite significant advances in the field of specular highlight removal in recent years, existing methods predominantly focus on natural images, where highlights typically appear on raised or edged surfaces of objects. These highlights are often small and sparsely distributed. However, for text imag…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

PHR-DIFF: Portrait Highlights Removal via Patch-aware Diffusion Model

Hongsheng Zheng, Zhongyun Bao, Gang Fu, Xuze Jiao, Chunxia Xiao
AAAI 2025technical

Portraits often suffer from specular highlights due to factors like skin oiliness, lighting conditions, and shooting angles, which degrade aesthetics and affect downstream tasks. Thus, portrait highlight removal is imperative. Previous methods struggle to remove highlights and achieve high-fidelity…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Correlation Matching Transformation Transformers for UHD Image Restoration

Cong Wang, Jinshan Pan, Wei Wang, Gang Fu, Siyuan Liang, Mengzhu Wang +2
AAAI 2024technical

This paper proposes UHDformer, a general Transformer for Ultra-High-Definition (UHD) image restoration. UHDformer contains two learning spaces: (a) learning in high-resolution space and (b) learning in low-resolution space. The former learns multi-level high-resolution features and fuses low-high fe…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗
2024

Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions

Adel Javanmard, Lin Chen, Vahab Mirrokni, Ashwinkumar Badanidiyuru, Gang Fu
ICLR 2024poster

Due to the rise of privacy concerns, in many practical applications, the training data is aggregated before being shared with the learner to protect the privacy of users' sensitive responses. In an aggregate learning framework, the dataset is grouped into bags of samples, where each bag is available…

Cited by 2Source ↗PDF ↗Scholar ↗
2024

SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization

Taisuke Yasuda, Kyriakos Axiotis, Gang Fu, Mohammadhossein Bateni, Vahab Mirrokni
NeurIPS 2024poster

Neural network pruning is a key technique towards engineering large yet scalable, interpretable, and generalizable models. Prior work on the subject has developed largely along two orthogonal directions: (1) differentiable pruning for efficiently and accurately scoring the importance of parameters,…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Two-Stage Video Shadow Detection via Temporal-Spatial Adaption

Xin Duan, Yu Cao, Lei Zhu, Gang Fu, Xin Wang, Renjie ZHANG +1
ECCV 2024poster

"Video Shadow Detection (VSD) is an important computer vision task focusing on detecting and segmenting shadows throughout the entire video sequence. Despite their remarkable performance, existing VSD methods and datasets mainly focus on the dominant and isolated shadows. Consequently, VSD under com…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2023

Approximately Optimal Core Shapes for Tensor Decompositions

Mehrdad Ghadiri, Matthew Fahrbach, Gang Fu, Vahab Mirrokni
ICML 2023poster

This work studies the combinatorial optimization problem of finding an optimal core tensor shape, also called multilinear rank, for a size-constrained Tucker decomposition. We give an algorithm with provable approximation guarantees for its reconstruction error via connections to higher-order singul…

Cited by 8Source ↗PDF ↗Scholar ↗
2023

Sequential Attention for Feature Selection

Taisuke Yasuda, Mohammadhossein Bateni, Lin Chen, Matthew Fahrbach, Gang Fu, Vahab Mirrokni
ICLR 2023poster

Feature selection is the problem of selecting a subset of features for a machine learning model that maximizes model quality subject to a budget constraint. For neural networks, prior methods, including those based on $\ell_1$ regularization, attention, and other techniques, typically select the ent…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2023

Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data

Gang Fu, Qing Zhang, Lei Zhu, Chunxia Xiao, Ping Li
ICCV 2023poster

This paper aims to remove specular highlights from a single object-level image. Although previous methods have made some progresses, their performance remains somewhat limited, particularly for real images with complex specular highlights. To this end, we propose a three-stage network to address the…

Cited by 14PDF ↗code ↗Scholar ↗
2022

Deep Image-Based Illumination Harmonization

Zhongyun Bao, Chengjiang Long, Gang Fu, Daquan Liu, Yuanzhen Li, Jiaming Wu +1
CVPR 2022poster

Integrating a foreground object into a background scenewith illumination harmonization is an important but chal-lenging task in computer vision and augmented reality community. Existing methods mainly focus on foreground andbackground appearance consistency or the foreground object shadow generation…

Cited by 18PDF ↗code ↗Scholar ↗
2022

Subquadratic Kronecker Regression with Applications to Tensor Decomposition

Matthew Fahrbach, Gang Fu, Mehrdad Ghadiri
NeurIPS 2022accept

Kronecker regression is a highly-structured least squares problem $\min_{\mathbf{x}} \lVert \mathbf{K}\mathbf{x} - \mathbf{b} \rVert_{2}^2$, where the design matrix $\mathbf{K} = \mathbf{A}^{(1)} \otimes \cdots \otimes \mathbf{A}^{(N)}$ is a Kronecker product of factor matrices. This regression prob…

Cited by 20Source ↗PDF ↗code ↗Scholar ↗
2021

A Multi-Task Network for Joint Specular Highlight Detection and Removal

Gang Fu, Qing Zhang, Lei Zhu, Ping Li, Chunxia Xiao
CVPR 2021poster

Specular highlight detection and removal are fundamental and challenging tasks. Although recent methods achieve promising results on the two tasks by supervised training on synthetic training data, they are typically solely designed for highlight detection or removal, and their performance usually d…

Cited by 100PDF ↗code ↗Scholar ↗
2019

Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond

Lin Chen, Hossein Esfandiari, Gang Fu, Vahab Mirrokni
NeurIPS 2019poster

Computing approximate nearest neighbors in high dimensional spaces is a central problem in large-scale data mining with a wide range of applications in machine learning and data science. A popular and effective technique in computing nearest neighbors approximately is the locality-sensitive hashing…

Cited by 18Source ↗PDF ↗Scholar ↗
2016

Greedy Column Subset Selection: New Bounds and Distributed Algorithms

Jason Altschuler, Aditya Bhaskara, Gang Fu, Vahab Mirrokni, Afshin Rostamizadeh, Morteza Zadimoghaddam
ICML 2016poster

The problem of column subset selection has recently attracted a large body of research, with feature selection serving as one obvious and important application. Among the techniques that have been applied to solve this problem, the greedy algorithm has been shown to be quite effective in practice. H…

Cited by 90Source ↗PDF ↗Scholar ↗