Adding Seemingly Uninformative Labels Helps in Low Data Regimes

2 code implementations • ICML 2020 • Christos Matsoukas, Albert Bou I Hernandez, Yue Liu, Karin Dembrower, Gisele Miranda, Emir Konuk, Johan Fredin Haslum, Athanasios Zouzos, Peter Lindholm, Fredrik Strand, Kevin Smith

Evidence suggests that networks trained on large datasets generalize well not solely because of the numerous training examples, but also class diversity which encourages learning of enriched features.

Tumor Segmentation