no code implementations • 12 Mar 2024 • Emanuel Ben-Baruch, Adam Botach, Igor Kviatkovsky, Manoj Aggarwal, Gérard Medioni
In this paper we explore the application of data pruning while incorporating knowledge distillation (KD) when training on a pruned subset.
1 code implementation • 29 Oct 2023 • Alon Shoshan, Nadav Bhonker, Emanuel Ben Baruch, Ori Nizan, Igor Kviatkovsky, Joshua Engelsma, Manoj Aggarwal, Gerard Medioni
We demonstrate the merits of FPGAN-Control, both quantitatively and qualitatively, in terms of identity preservation level, degree of appearance control, and low synthetic-to-real domain gap.
no code implementations • 25 Oct 2022 • Steven A. Grosz, Joshua J. Engelsma, Rajeev Ranjan, Naveen Ramakrishnan, Manoj Aggarwal, Gerard G. Medioni, Anil K. Jain
We further demonstrate that by guiding the ViT to focus in on local, minutiae related features, we can boost the recognition performance.
no code implementations • 22 Apr 2022 • Jiuhong Xiao, Lavisha Aggarwal, Prithviraj Banerjee, Manoj Aggarwal, Gerard Medioni
We present a novel Identity Preserving Reconstruction (IPR) loss function which achieves Bits-Per-Pixel (BPP) values that are ~38% and ~42% of CRF-23 HEVC compression for LFW (low-resolution) and CelebA-HQ (high-resolution) datasets, respectively, while maintaining parity in recognition accuracy.