12 papers
The Role of Gradient Modification in Heavy-Tailed Nonconvex Stochastic Min-Max Optimization
Tianxi Zhu, Yi Xu, Xiangyang Ji
Stochastic min-max optimization has attracted increasing attention due to its applications in modern machine learning, while existing theoretical studies mainly rely on the bounded…
LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection
Tianfang Zhang, Lei Li, Chang Liu +3
Infrared small target detection (IRSTD) aims to identify long distance small targets from complex infrared backgrounds, and is a fundamental task in remote sensing. Deep learning m…
ConformalSAM: Unlocking the Potential of Foundational Segmentation Models in Semi-Supervised Semantic Segmentation with Conformal Prediction
Danhui Chen, Ziquan Liu, Chuxi Yang +4
Pixel-level vision tasks, such as semantic segmentation, require extensive and high-quality annotated data, which is costly to obtain. Semi-supervised semantic segmentation (SSSS)…
Stochastic Weakly Convex Optimization Under Heavy-Tailed Noises
Tianxi Zhu, Yi Xu, Xiangyang Ji
An increasing number of studies have focused on stochastic first-order methods (SFOMs) under heavy-tailed gradient noises, which have been observed in the training of practical dee…
Score-Based Model for Low-Rank Tensor Recovery
Zhengyun Cheng, Changhao Wang, Guanwen Zhang +3
Low-rank tensor decompositions (TDs) provide an effective framework for multiway data analysis. Traditional TD methods rely on predefined structural assumptions, such as CP or Tuck…
Low-Rank Tensor Recovery via Variational Schatten-p Quasi-Norm and Jacobian Regularization
Zhengyun Cheng, Ruizhe Zhang, Guanwen Zhang +3
Higher-order tensors are well-suited for representing multi-dimensional data, such as images and videos, which typically characterize low-rank structures. Low-rank tensor decomposi…
The Solution for Single Object Tracking Task of Perception Test Challenge 2024
Zhiqiang Zhong, Yang Yang, Fengqiang Wan +2
This report presents our method for Single Object Tracking (SOT), which aims to track a specified object throughout a video sequence. We employ the LoRAT method. The essence of the…
Efficient Personalized Text-to-image Generation by Leveraging Textual Subspace
Shian Du, Xiaotian Cheng, Qi Qian +3
Personalized text-to-image generation has attracted unprecedented attention in the recent few years due to its unique capability of generating highly-personalized images via using…
The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
Ziquan Liu, Yufei Cui, Yan Yan +4
In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient health and road safety, it is imperative to m…
Solution for Point Tracking Task of ICCV 1st Perception Test Challenge 2023
Hongpeng Pan, Yang Yang, Zhongtian Fu +4
This report proposes an improved method for the Tracking Any Point (TAP) task, which tracks any physical surface through a video. Several existing approaches have explored the TAP…
SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving
Yiming Xie, Henglu Wei, Zhenyi Liu +2
To advance research in learning-based defogging algorithms, various synthetic fog datasets have been developed. However, existing datasets created using the Atmospheric Scattering…
ParCo: Part-Coordinating Text-to-Motion Synthesis
Qiran Zou, Shangyuan Yuan, Shian Du +5
We study a challenging task: text-to-motion synthesis, aiming to generate motions that align with textual descriptions and exhibit coordinated movements. Currently, the part-based…