Search Results for author:
Found 2 papers, 0 papers with code
Long-Range Zero-Shot Generative Deep Network Quantization
We find it is because: 1) a normal generator is hard to obtain high diversity of synthetic data, since it lacks long-range information to allocate attention to global features; 2) the synthetic images aim to simulate the statistics of real data, which leads to weak intra-class heterogeneity and limited feature richness.
Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization
To obtain high inter-class separability of semantic features, we cluster and align the feature distribution statistics to imitate the distribution of real data, so that the performance degradation is alleviated.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
