Overcoming Research Hurdles
Mathilde shares her experiences with the challenges faced during a project that aimed to integrate improvements from the simclr paper into deep cluster. Despite initial success, issues arose with the fluctuating loss due to the need to reset the final classification layer at each epoch, highlighting the complexities of adapting research methods in practice.In this clip
From this podcast
Machine Learning Street Talk (MLST)
SWaV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (Mathilde Caron)
Related Questions