CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning

arXiv:2311.14272v2 Announce Type: replace-cross
Abstract: Machine learning pipelines for classification tasks often train a universal model to achieve accuracy across a broad range of classes. However, a typical user encounters only a limited selection of classes regularly. This disparity provides an opportunity to enhance computational efficiency by tailoring models to focus on user-specific classes. Existing works rely on unstructured pruning, which introduces randomly distributed non-zero values in the model, making it unsuitable for hardware acceleration. Alternatively, some approaches employ structured …

arxiv class cs.ar cs.cv cs.lg hybrid pruning sparsity type