activity
20182020
most citedDepthwise Convolution is All You Need for Learning Multiple Visual Domains

33 citations · 40 across the 3 of their papers we have counts for

collaborators

8 papers

cs.LG20202 cited

SHEARer: Highly-Efficient Hyperdimensional Computing by Software-Hardware Enabled Multifold Approximation

Behnam Khaleghi, Sahand Salamat, Anthony Thomas +3

Hyperdimensional computing (HD) is an emerging paradigm for machine learning based on the evidence that the brain computes on high-dimensional, distributed, representations of data…

cs.CV20195 cited

AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning

Yunhui Guo, Yandong Li, Liqiang Wang +1

There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which a…

cs.CV2019

A Broader Study of Cross-Domain Few-Shot Learning

Yunhui Guo, Noel C. Codella, Leonid Karlinsky +5

Recent progress on few-shot learning largely relies on annotated data for meta-learning: base classes sampled from the same domain as the novel classes. However, in many applicatio…

cs.LG2019

Improved Schemes for Episodic Memory-based Lifelong Learning

Yunhui Guo, Mingrui Liu, Tianbao Yang +1

Current deep neural networks can achieve remarkable performance on a single task. However, when the deep neural network is continually trained on a sequence of tasks, it seems to g…

cs.AR2019

Workload-Aware Opportunistic Energy Efficiency in Multi-FPGA Platforms

Sahand Salamat, Behnam Khaleghi, Mohsen Imani +1

The continuous growth of big data applications with high computational and scalability demands has resulted in increasing popularity of cloud computing. Optimizing the performance…

cs.CV201933 cited

Depthwise Convolution is All You Need for Learning Multiple Visual Domains

Yunhui Guo, Yandong Li, Rogerio Feris +2

There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can…