all AI news
Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning. (arXiv:2102.06866v5 [cs.LG] UPDATED)
Jan. 17, 2022, 2:10 a.m. | Kento Nozawa, Issei Sato
cs.LG updates on arXiv.org arxiv.org
Instance discriminative self-supervised representation learning has been
attracted attention thanks to its unsupervised nature and informative feature
representation for downstream tasks. In practice, it commonly uses a larger
number of negative samples than the number of supervised classes. However,
there is an inconsistency in the existing analysis; theoretically, a large
number of negative samples degrade classification performance on a downstream
supervised task, while empirically, they improve the performance. We provide a
novel framework to analyze this empirical result regarding negative …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote