3 papers
cs.CV2024
PNVC: Towards Practical INR-based Video Compression
Ge Gao, Ho Man Kwan, Fan Zhang +1
Neural video compression has recently demonstrated significant potential to compete with conventional video codecs in terms of rate-quality performance. These learned video codecs…
cs.LG2023
FedSDD: Scalable and Diversity-enhanced Distillation for Model Aggregation in Federated Learning
Ho Man Kwan, Shenghui Song
Recently, innovative model aggregation methods based on knowledge distillation (KD) have been proposed for federated learning (FL). These methods not only improved the robustness o…
cs.CV2022
SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling
Ho Man Kwan, Shenghui Song
Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and…