Showing cs.CVShow all
3 papers · 1 filter
cs.CV2024
Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers
Binxiao Huang, Jason Chun Lok, Chang Liu +1
Poisoning-based backdoor attacks expose vulnerabilities in the data preparation stage of deep neural network (DNN) training. The DNNs trained on the poisoned dataset will be embedd…
cs.CV2023
Learning Spatially Collaged Fourier Bases for Implicit Neural Representation
Jason Chun Lok Li, Chang Liu, Binxiao Huang +1
Existing approaches to Implicit Neural Representation (INR) can be interpreted as a global scene representation via a linear combination of Fourier bases of different frequencies.…
cs.CV2023
A Unifying Tensor View for Lightweight CNNs
Jason Chun Lok Li, Rui Lin, Jiajun Zhou +2
Despite the decomposition of convolutional kernels for lightweight CNNs being well studied, existing works that rely on tensor network diagrams or hyperdimensional abstraction lack…