Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Models
Donghoon Kim, Dongyoung Lee, Ik Joon Chang +1
Diffusion models achieve high-quality image generation but face deployment challenges due to their high computational requirements. Although 8-bit outlier-aware post-training quant…
cs.CV2023
Robustness of SAM: Segment Anything Under Corruptions and Beyond
Yu Qiao, Chaoning Zhang, Taegoo Kang +3
Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance…