Publications (13)
Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment
Hong Li, Zhen Zhou, Honggang Zhang +4
Data-parallel (DP) training with synchronous all-reduce is a dominant paradigm for full-parameter fine-tuning of large language models (LLMs). While parameter synchronization guara…
Simple Primary Colour Editing for Consumer Product Images
Han Gong, Luwen Yu, Stephen Westland
We present a simple primary colour editing method for consumer product images. We show that by using colour correction and colour blending, we can automate the pain-staking colour…
Interactive Removal and Ground Truth for Difficult Shadow Scenes
Han Gong, Darren P. Cosker
A user-centric method for fast, interactive, robust and high-quality shadow removal is presented. Our algorithm can perform detection and removal in a range of difficult cases: suc…
Interactive Illumination Invariance
Han Gong, Graham Finlayson
Illumination effects cause problems for many computer vision algorithms. We present a user-friendly interactive system for robust illumination-invariant image generation. Compared…
Concise Radiometric Calibration Using The Power of Ranking
Han Gong, Graham D. Finlayson, Maryam M. Darrodi
Compared with raw images, the more common JPEG images are less useful for machine vision algorithms and professional photographers because JPEG-sRGB does not preserve a linear rela…
Color Homography Color Correction
Graham D. Finlayson, Han Gong, Robert B. Fisher
Homographies -- a mathematical formalism for relating image points across different camera viewpoints -- are at the foundations of geometric methods in computer vision and are used…