High-quality Single-model Deep Video Compression with Frame-Conv3D and Multi-frame Differential Modulation

no code implementations • ECCV 2020 • Wenyu Sun, Chen Tang, Weigui Li, Zhuqing Yuan, Huazhong Yang, Yongpan Liu

This paper proposes a deep video compression method to simultaneously encode multiple frames with Frame-Conv3D and differential modulation.

Quantization Video Compression

Adaptive Pixel-wise Structured Sparse Network for Efficient CNNs

no code implementations • 21 Oct 2020 • Chen Tang, Wenyu Sun, Zhuqing Yuan, Yongpan Liu

To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image.

General Classification Image Classification +4

ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression

no code implementations • 7 Jun 2020 • Xiaoyu Feng, Zhuqing Yuan, Guijin Wang, Yongpan Liu

For example, the model is first pruned on the cloud and then transferred from cloud to end by UDA.

Knowledge Distillation Network Pruning +2