1 code implementation • 7 May 2024 • Guanghao Wei, Yining Huang, Chenru Duan, Yue Song, Yuanqi Du
In this paper, we propose a new framework, ChemFlow, to traverse chemical space through navigating the latent space learned by molecule generative models through flows.
1 code implementation • 17 Mar 2024 • Ziheng Chen, Yue Song, Yunmei Liu, Nicu Sebe
Using the deformation concept, we generalize the existing Lie groups on SPD manifolds into three families of parameterized Lie groups.
1 code implementation • 10 Dec 2023 • Zhihang Yuan, Yuzhang Shang, Yue Song, Qiang Wu, Yan Yan, Guangyu Sun
Based on the success of the low-rank decomposition of projection matrices in the self-attention module, we further introduce ASVD to compress the KV cache.
1 code implementation • 23 Nov 2023 • Yue Song, Nicu Sebe, Wei Wang
This observation motivates us to propose \texttt{RankFeat}, a simple yet effective \emph{post hoc} approach for OOD detection by removing the rank-1 matrix composed of the largest singular value and the associated singular vectors from the high-level feature.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
1 code implementation • NeurIPS 2023 • Yue Song, T. Anderson Keller, Nicu Sebe, Max Welling
A prominent goal of representation learning research is to achieve representations which are factorized in a useful manner with respect to the ground truth factors of variation.
1 code implementation • ICCV 2023 • Yue Song, Jichao Zhang, Nicu Sebe, Wei Wang
Generative Adversarial Networks (GANs), especially the recent style-based generators (StyleGANs), have versatile semantics in the structured latent space.
1 code implementation • 18 May 2023 • Ziheng Chen, Yue Song, Gaowen Liu, Ramana Rao Kompella, XiaoJun Wu, Nicu Sebe
Besides, our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks.
1 code implementation • 25 Apr 2023 • Yue Song, T. Anderson Keller, Nicu Sebe, Max Welling
In this work, we instead propose to model latent structures with a learned dynamic potential landscape, thereby performing latent traversals as the flow of samples down the landscape's gradient.
no code implementations • 26 Mar 2023 • Ziheng Chen, Yue Song, Tianyang Xu, Zhiwu Huang, Xiao-Jun Wu, Nicu Sebe
Symmetric Positive Definite (SPD) matrices have received wide attention in machine learning due to their intrinsic capacity of encoding underlying structural correlation in data.
no code implementations • 15 Feb 2023 • Jiazuo Hou, Fei Teng, Wenqian Yin, Yue Song, Yunhe Hou
With any given cyber-defense resource, this paper proposes a preventive-corrective cyber-defense strategy, which minimizes the FDI attack-induced region in a preventive manner, followed by maximizing the cybersecurity margin in a corrective manner.
no code implementations • 4 Feb 2023 • Jun Wang, Yue Song, David John Hill, Yunhe Hou, Feilong Fan
To figure out the stability issues brought by renewable energy sources (RES) with non-Gaussian uncertainties in isolated microgrids, this paper proposes a chance constrained stability constrained optimal power flow (CC-SC-OPF) model.
1 code implementation • 11 Dec 2022 • Yue Song, Nicu Sebe, Wei Wang
Extensive experiments on visual recognition demonstrate that our methods can simultaneously improve covariance conditioning and generalization.
no code implementations • 18 Sep 2022 • Tong Han, Yue Song, David J. Hill
The topology transition problem of transmission networks is becoming increasingly crucial with topological flexibility more widely leveraged to promote high renewable penetration.
1 code implementation • 18 Sep 2022 • Yue Song, Nicu Sebe, Wei Wang
The task of out-of-distribution (OOD) detection is crucial for deploying machine learning models in real-world settings.
no code implementations • 22 Aug 2022 • Tong Han, David J. Hill, Yue Song
This aims to find the topology transition trajectory from an initial topology to a desired terminal topology, which optimizes certain transition performance and satisfies operational constraints.
1 code implementation • 9 Jul 2022 • Yue Song, Nicu Sebe, Wei Wang
EigenDecomposition (ED) is at the heart of many computer vision algorithms and applications.
1 code implementation • 5 Jul 2022 • Yue Song, Nicu Sebe, Wei Wang
Inserting an SVD meta-layer into neural networks is prone to make the covariance ill-conditioned, which could harm the model in the training stability and generalization abilities.
1 code implementation • 26 May 2022 • Yue Song, Nicu Sebe, Wei Wang
Inspired by this observation, we propose a network branch dedicated to magnifying the importance of small eigenvalues.
Ranked #5 on Fine-Grained Image Classification on Stanford Dogs
Fine-Grained Image Classification Fine-Grained Visual Categorization +1
1 code implementation • CVPR 2023 • Bin Ren, Yahui Liu, Yue Song, Wei Bi, Rita Cucchiara, Nicu Sebe, Wei Wang
In particular, MJP first shuffles the selected patches via our block-wise random jigsaw puzzle shuffle algorithm, and their corresponding PEs are occluded.
no code implementations • 23 May 2022 • Wenbo Su, Yuanxing Zhang, Yufeng Cai, Kaixu Ren, Pengjie Wang, Huimin Yi, Yue Song, Jing Chen, Hongbo Deng, Jian Xu, Lin Qu, Bo Zheng
High-concurrency asynchronous training upon parameter server (PS) architecture and high-performance synchronous training upon all-reduce (AR) architecture are the most commonly deployed distributed training modes for recommendation models.
1 code implementation • 11 Apr 2022 • Yuanxing Zhang, Langshi Chen, Siran Yang, Man Yuan, Huimin Yi, Jie Zhang, Jiamang Wang, Jianbo Dong, Yunlong Xu, Yue Song, Yong Li, Di Zhang, Wei Lin, Lin Qu, Bo Zheng
However, we observe that GPU devices in training recommender systems are underutilized, and they cannot attain an expected throughput improvement as what it has achieved in CV and NLP areas.
no code implementations • 8 Feb 2022 • Yue Song, Hao Tang, Nicu Sebe, Wei Wang
Specifically, the detail modeling focuses on capturing the object edges by supervision of explicitly decomposed detail label that consists of the pixels that are nested on the edge and near the edge.
no code implementations • 6 Feb 2022 • Tong Han, David J. Hill, Yue Song
This paper focuses on the issue of network connectedness (NC) in security-constrained optimal transmission switching problems, which is complicated by branch contingencies and corrective line switching.
1 code implementation • 29 Jan 2022 • Yue Song, Nicu Sebe, Wei Wang
Computing the matrix square root and its inverse in a differentiable manner is important in a variety of computer vision tasks.
1 code implementation • ICLR 2022 • Yue Song, Nicu Sebe, Wei Wang
Previous methods either adopt the Singular Value Decomposition (SVD) to explicitly factorize the matrix or use the Newton-Schulz iteration (NS iteration) to derive the approximate solution.
no code implementations • 23 Jul 2021 • Yue Song, Tao Liu, David J. Hill
In the proposed model, both power generations and line susceptances are continuous variables to minimize the expected generation cost and guarantee a low probability of constraint violation in terms of generations and line flows under renewable uncertainties.
1 code implementation • ICCV 2021 • Yue Song, Nicu Sebe, Wei Wang
Singular Value Decomposition (SVD) is used in GCP to compute the matrix square root.