← Search

Yanshu Wang

2 accepted papers

2025

FAST: Foreground‑aware Diffusion with Accelerated Sampling Trajectory for Segmentation‑oriented Anomaly Synthesis

NeurIPS 2025poster

Industrial anomaly segmentation relies heavily on pixel-level annotations, yet real-world anomalies are often scarce, diverse, and costly to label. Segmentation-oriented industrial anomaly synthesis (SIAS) has emerged as a promising alternative; however, existing methods struggle to balance sampling…

Cited by 0SourcecodeScholar
2018

BML: A High-performance, Low-cost Gradient Synchronization Algorithm for DML Training

NeurIPS 2018poster

In distributed machine learning (DML), the network performance between machines significantly impacts the speed of iterative training. In this paper we propose BML, a new gradient synchronization algorithm with higher network performance and lower network cost than the current practice. BML runs on…

Cited by 39SourcePDFScholar