The computer vision model compression approach developed by the authors compresses model parameters by approximately 50× and reduces model size by 75% on CIFAR-10, CIFAR-100, and ImageNet1k benchmarks, while maintaining accuracy and uncertainty estimations comparable to state-of-the-art methods.

Authors

• Person: Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche Organization: AISTATS
  Track: Poster Session 3 - aistats 2026

Sources

• Track: Poster Session 3 - aistats 2026 virtual.aistats.org Samuel Tesfazgi, Leonhard Sprandl, Sandra Hirche · AISTATS via serper

Referenced by nodes (1)

• computer vision concept