16 citations · 16 across the 2 of their papers we have counts for
3 papers
cs.CV2021
Pretrained equivariant features improve unsupervised landmark discovery
Rahul Rahaman, Atin Ghosh, Alexandre H. Thiery
Locating semantically meaningful landmark points is a crucial component of a large number of computer vision pipelines. Because of the small number of available datasets with groun…
stat.ML2021★ 16 cited
On Data-Augmentation and Consistency-Based Semi-Supervised Learning
Atin Ghosh, Alexandre H. Thiery
Recently proposed consistency-based Semi-Supervised Learning (SSL) methods such as the -model, temporal ensembling, the mean teacher, or the virtual adversarial training, have a…
cs.LG2018
ARMDN: Associative and Recurrent Mixture Density Networks for eRetail Demand Forecasting
Srayanta Mukherjee, Devashish Shankar, Atin Ghosh +4
Accurate demand forecasts can help on-line retail organizations better plan their supply-chain processes. The challenge, however, is the large number of associative factors that re…