Search Results for author:
Found 6 papers, 4 papers with code
Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Network
In this work, we propose the Shrinking SNN (SSNN) to achieve low-latency neuromorphic object recognition without reducing performance.
Ranked #1 on
Event data classification
on N-Caltech 101
(Accuracy (% ) metric)
Order-preserving Consistency Regularization for Domain Adaptation and Generalization
To alleviate this problem, data augmentation coupled with consistency regularization are commonly adopted to make the model less sensitive to domain-specific attributes.
Variational Model Perturbation for Source-Free Domain Adaptation
Our model perturbation provides a new probabilistic way for domain adaptation which enables efficient adaptation to target domains while maximally preserving knowledge in source models.
Alleviating Feature Confusion for Generative Zero-shot Learning
An inevitable issue of such a paradigm is that the synthesized unseen features are prone to seen references and incapable to reflect the novelty and diversity of real unseen instances.
Agile Domain Adaptation
Because of the distribution shifts, different target samples have distinct degrees of difficulty in adaptation.
From Zero-Shot Learning to Cold-Start Recommendation
This work, for the first time, formulates CSR as a ZSL problem, and a tailor-made ZSL method is proposed to handle CSR.
