Search Results for author:
Found 4 papers, 2 papers with code
CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning
Machine learning pipelines for classification tasks often train a universal model to achieve accuracy across a broad range of classes.
Post-Training Quantization with Low-precision Minifloats and Integers on FPGAs
However, the exploration of floating-point formats smaller than 8 bits and their comparison with integer quantization remains relatively limited.
Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay
In particular, we design a Variational Autoencoder (VAE) with a training objective that is customized to learn the synthetic data representations optimally.
Synthetic Video Generation for Robust Hand Gesture Recognition in Augmented Reality Applications
The goal of this work is to introduce a framework capable of generating photo-realistic videos that have labelled hand bounding box and fingertip that can help in designing, training, and benchmarking models for hand-gesture recognition in AR/VR applications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
