1 citations · 1 across the 4 of their papers we have counts for
3 papers · 1 filter
Multi Positive Contrastive Learning with Pose-Consistent Generated Images
Sho Inayoshi, Aji Resindra Widya, Satoshi Ozaki +2
Model pre-training has become essential in various recognition tasks. Meanwhile, with the remarkable advancements in image generation models, pre-training methods utilizing generat…
Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter
Yuiko Sakuma, Masakazu Yoshimura, Junji Otsuka +2
Compression of large and performant vision foundation models (VFMs) into arbitrary bit-wise operations (BitOPs) allows their deployment on various hardware. We propose to fine-tune…
Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection
Junji Otsuka, Masakazu Yoshimura, Takeshi Ohashi
Unprocessed sensor outputs (RAW images) potentially improve both low-level and high-level computer vision algorithms, but the lack of large-scale RAW image datasets is a barrier to…