198 citations · 1k across the 28 of their papers we have counts for
28 papers
Bag of Tricks and A Strong baseline for Image Copy Detection
Wenhao Wang, Weipu Zhang, Yifan Sun +1
Image copy detection is of great importance in real-life social media. In this paper, a bag of tricks and a strong baseline are proposed for image copy detection. Unsupervised pre-…
DLV: A Data-Driven and Local-Verification Approach for Image Copy Detection
Wenhao Wang, Yifan Sun, Weipu Zhang +1
Image copy detection is of great importance in real-life social media. In this paper, a data-driven and local-verification (DLV) approach is proposed to compete for Image Simil…
Bumblebee: A Path Towards Fully Autonomous Robotic Vine Pruning
Abhisesh Silwal, Francisco Yandun, Anjana Nellithimaru +2
Dormant season grapevine pruning requires skilled seasonal workers during the winter season which are becoming less available. As workers hasten to prune more vines in less time am…
Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework
Tengteng Huang, Yifan Sun, Xun Wang +2
Model smoothing is of central importance for obtaining a reliable teacher model in the student-teacher framework, where the teacher generates surrogate supervision signals to train…
IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID
Yongxing Dai, Jun Liu, Yifan Sun +3
Unsupervised domain adaptive person re-identification (UDA re-ID) aims at transferring the labeled source domain's knowledge to improve the model's discriminability on the unlabele…
Approximate Frank-Wolfe Algorithms over Graph-structured Support Sets
Baojian Zhou, Yifan Sun
In this paper, we consider approximate Frank-Wolfe (FW) algorithms to solve convex optimization problems over graph-structured support sets where the linear minimization oracle (LM…
Continuous Time Frank-Wolfe Does Not Zig-Zag, But Multistep Methods Do Not Accelerate
Zhaoyue Chen, Mokhwa Lee, Yifan Sun
The Frank-Wolfe algorithm has regained much interest in its use in structurally constrained machine learning applications. However, one major limitation of the Frank-Wolfe algorith…
Daisen: A Framework for Visualizing Detailed GPU Execution
Yifan Sun, Yixuan Zhang, Ali Mosallaei +3
Graphics Processing Units (GPUs) have been widely used to accelerate artificial intelligence, physics simulation, medical imaging, and information visualization applications. To im…
Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
Yifan Sun, Yuke Zhu, Yuhan Zhang +4
This paper introduces a new fundamental characteristic, \ie, the dynamic range, from real-world metric tools to deep visual recognition. In metrology, the dynamic range is a basic…
Mapping the Landscape of COVID-19 Crisis Visualizations
Yixuan Zhang, Yifan Sun, Lace Padilla +3
In response to COVID-19, a vast number of visualizations have been created to communicate information to the public. Information exposure in a public health crisis can impact peopl…
Latent Group Structured Multi-task Learning
Xiangyu Niu, Yifan Sun, Jinyuan Sun
In multi-task learning (MTL), we improve the performance of key machine learning algorithms by training various tasks jointly. When the number of tasks is large, modeling task stru…
MGPU-TSM: A Multi-GPU System with Truly Shared Memory
Saiful A. Mojumder, Yifan Sun, Leila Delshadtehrani +6
The sizes of GPU applications are rapidly growing. They are exhausting the compute and memory resources of a single GPU, and are demanding the move to multiple GPUs. However, the p…
Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory
Jialun Liu, Jingwei Zhang, Yi yang +3
This paper considers deep visual recognition on long-tailed data. To be general, we consider two applied scenarios, \ie, deep classification and deep metric learning. Under the lon…
CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions
Zhongdao Wang, Jingwei Zhang, Liang Zheng +4
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as t…
HALCONE : A Hardware-Level Timestamp-based Cache Coherence Scheme for Multi-GPU systems
Saiful A. Mojumder, Yifan Sun, Leila Delshadtehrani +6
While multi-GPU (MGPU) systems are extremely popular for compute-intensive workloads, several inefficiencies in the memory hierarchy and data movement result in a waste of GPU reso…
Embodied Self-supervised Learning by Coordinated Sampling and Training
Yifan Sun, Xihong Wu
Self-supervised learning can significantly improve the performance of downstream tasks, however, the dimensions of learned representations normally lack explicit physical meanings.…
Circle Loss: A Unified Perspective of Pair Similarity Optimization
Yifan Sun, Changmao Cheng, Yuhan Zhang +4
This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity and minimize the between-class similarit…
Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective
Jialun Liu, Yifan Sun, Chuchu Han +2
This paper considers learning deep features from long-tailed data. We observe that in the deep feature space, the head classes and the tail classes present different distribution p…
Summarizing CPU and GPU Design Trends with Product Data
Yifan Sun, Nicolas Bohm Agostini, Shi Dong +1
Moore's Law and Dennard Scaling have guided the semiconductor industry for the past few decades. Recently, both laws have faced validity challenges as transistor sizes approach the…
Vehicle Re-identification with Viewpoint-aware Metric Learning
Ruihang Chu, Yifan Sun, Yadong Li +3
This paper considers vehicle re-identification (re-ID) problem. The extreme viewpoint variation (up to 180 degrees) poses great challenges for existing approaches. Inspired by the…
Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
Yifan Sun, Qin Xu, Yali Li +4
This paper considers a realistic problem in person re-identification (re-ID) task, i.e., partial re-ID. Under partial re-ID scenario, the images may contain a partial observation o…
MGSim + MGMark: A Framework for Multi-GPU System Research
Yifan Sun, Trinayan Baruah, Saiful A. Mojumder +10
The rapidly growing popularity and scale of data-parallel workloads demand a corresponding increase in raw computational power of GPUs (Graphics Processing Units). As single-GPU sy…
ADMM for combinatorial graph problems
Chuangchuang Sun, Yifan Sun, Ran Dai
We investigate a class of general combinatorial graph problems, including MAX-CUT and community detection, reformulated as quadratic objectives over nonconvex constraints and solve…
Deep Unsupervised Clustering Using Mixture of Autoencoders
Dejiao Zhang, Yifan Sun, Brian Eriksson +1
Unsupervised clustering is one of the most fundamental challenges in machine learning. A popular hypothesis is that data are generated from a union of low-dimensional nonlinear man…