← Search

Weixin Feng

2 accepted papers

2024

Accelerating Image Generation with Sub-path Linear Approximation Model

ECCV 2024oral

"Diffusion models have significantly advanced the state of the art in image, audio, and video generation tasks. However, their applications in practical scenarios are hindered by slow inference speed. Drawing inspiration from the consistency models, we propose the Sub-Path Linear Approximation Model…

Cited by 10SourcePDFScholar
2021

Temporal Knowledge Consistency for Unsupervised Visual Representation Learning

ICCV 2021poster

The instance discrimination paradigm has become dominant in unsupervised learning. It always adopts a teacher-student framework, in which the teacher provides embedded knowledge as a supervision signal for the student. The student learns meaningful representations by enforcing instance spatial consi…

Cited by 13PDFcodeScholar