71 citations · 416 across the 50 of their papers we have counts for
7 papers · 1 filter
Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation
Gaurav Patel, Konda Reddy Mopuri, Qiang Qiu
Data-free Knowledge Distillation (DFKD) has gained popularity recently, with the fundamental idea of carrying out knowledge transfer from a Teacher neural network to a Student neur…
Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?
Sheikh Shams Azam, Seyyedali Hosseinalipour, Qiang Qiu +1
In this paper, we question the rationale behind propagating large numbers of parameters through a distributed system during federated learning. We start by examining the rank chara…
TESSERACT: Gradient Flip Score to Secure Federated Learning Against Model Poisoning Attacks
Atul Sharma, Wei Chen, Joshua Zhao +3
Federated learning---multi-party, distributed learning in a decentralized environment---is vulnerable to model poisoning attacks, even more so than centralized learning approaches.…
Using Text to Teach Image Retrieval
Haoyu Dong, Ze Wang, Qiang Qiu +1
Image retrieval relies heavily on the quality of the data modeling and the distance measurement in the feature space. Building on the concept of image manifold, we first propose to…
Learning to Learn Variational Semantic Memory
Xiantong Zhen, Yingjun Du, Huan Xiong +3
In this paper, we introduce variational semantic memory into meta-learning to acquire long-term knowledge for few-shot learning. The variational semantic memory accrues and stores…
A Dictionary Approach to Domain-Invariant Learning in Deep Networks
Ze Wang, Xiuyuan Cheng, Guillermo Sapiro +1
In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Netw…
Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters
Wei Zhu, Qiang Qiu, Robert Calderbank +2
Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when deali…