activity
20172022
most citedGenerative Poisoning Attack Method Against Neural Networks

148 citations · 363 across the 27 of their papers we have counts for

collaborators
Showing cs.CVShow all

11 papers · 1 filter

cs.CV2021

The Untapped Potential of Off-the-Shelf Convolutional Neural Networks

Matthew Inkawhich, Nathan Inkawhich, Eric Davis +2

Over recent years, a myriad of novel convolutional network architectures have been developed to advance state-of-the-art performance on challenging recognition tasks. As computatio…

cs.CV20206 cited

ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition

Hsin-Pai Cheng, Feng Liang, Meng Li +5

Scale variance among different sizes of body parts and objects is a challenging problem for visual recognition tasks. Existing works usually design dedicated backbone or apply Neur…

cs.CV20208 cited

PENNI: Pruned Kernel Sharing for Efficient CNN Inference

Shiyu Li, Edward Hanson, Hai Li +1

Although state-of-the-art (SOTA) CNNs achieve outstanding performance on various tasks, their high computation demand and massive number of parameters make it difficult to deploy t…

cs.CV20204 cited

Defending against GAN-based Deepfake Attacks via Transformation-aware Adversarial Faces

Chaofei Yang, Lei Ding, Yiran Chen +1

Deepfake represents a category of face-swapping attacks that leverage machine learning models such as autoencoders or generative adversarial networks. Although the concept of the f…

cs.CV201913 cited

Trained Rank Pruning for Efficient Deep Neural Networks

Yuhui Xu, Yuxi Li, Shuai Zhang +7

To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attemp…

cs.CV2019

Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training

Chunpeng Wu, Wei Wen, Yiran Chen +1

Generative adversarial network (GAN) has greatly improved the quality of unsupervised image generation. Previous GAN-based methods often require a large amount of high-quality trai…