Search Results for author:
Found 8 papers, 3 papers with code
Differentiable Transportation Pruning
Deep learning algorithms are increasingly employed at the edge.
Understanding weight-magnitude hyperparameters in training binary networks
Our analysis makes it possible to understand how magnitude-based hyperparameters influence the training of binary networks which allows for new optimization filters specifically designed for binary neural networks that are independent of their real-valued interpretation.
Equal Bits: Enforcing Equally Distributed Binary Network Weights
We investigate experimentally that equal bit ratios are indeed preferable and show that our method leads to optimization benefits.
Less bits is more: How pruning deep binary networks increases weight capacity
We make the observation that pruning weights adds the value 0 as an additional symbol and thus increases the information capacity of the network.
Deep Unsupervised Image Hashing by Maximizing Bit Entropy
This layer is shown to minimize a penalized term of the Wasserstein distance between the learned continuous image features and the optimal half-half bit distribution.
Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels
Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training.
WeightAlign: Normalizing Activations by Weight Alignment
Such methods are less stable than BN as they critically depend on the statistics of a single input sample.
Push for Quantization: Deep Fisher Hashing
In this paper we push for quantization: We optimize maximum class separability in the binary space.
