5 papers
Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers
Edwin Kwadwo Tenagyei, Lei Wang, Ugochukwu Ejike Akpudo +2
Parameter-efficient fine-tuning (PEFT) has become a practical solution for adapting large pretrained vision transformers (ViTs) to downstream tasks while updating only a small subs…
Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
Puyu Wang, Jan Schuchardt, Nikita Kalinin +4
We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differenti…
Privacy-Aware Video Anomaly Detection through Orthogonal Subspace Projection
Lei Wang, Wenxiang Diao, Andrew Busch +2
Video anomaly detection (VAD) systems often prioritize accuracy while overlooking privacy concerns, limiting their suitability for real-world deployment. We propose the Orthogonal…
Visual Explanation via Similar Feature Activation for Metric Learning
Yi Liao, Ugochukwu Ejike Akpudo, Jue Zhang +4
Visual explanation maps enhance the trustworthiness of decisions made by deep learning models and offer valuable guidance for developing new algorithms in image recognition tasks.…
TraNCE: Transformative Non-linear Concept Explainer for CNNs
Ugochukwu Ejike Akpudo, Yongsheng Gao, Jun Zhou +1
Convolutional neural networks (CNNs) have succeeded remarkably in various computer vision tasks. However, they are not intrinsically explainable. While the feature-level understand…