most citedDeep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data

3 citations · 3 across the 3 of their papers we have counts for

collaborators

5 papers

eess.IV2020

Volumetric based mass flow estimation on sugarcane harvesters

Muhammad K. A. Hamdan, Diane T. Rover, Matthew J. Darr +1

Yield monitors on harvesters are a key component of precision agriculture. Mass flow estimation is the critical factor to measure, and having this allows for field productivity ana…

cs.CV2020

Generalizable semi-supervised learning method to estimate mass from sparsely annotated images

Muhammad K. A. Hamdan, Diane T. Rover, Matthew J. Darr +1

Mass flow estimation is of great importance to several industries, and it can be quite challenging to obtain accurate estimates due to limitation in expense or general infeasibilit…

cs.LG2020

Granular Learning with Deep Generative Models using Highly Contaminated Data

John Just

An approach to utilize recent advances in deep generative models for anomaly detection in a granular (continuous) sense on a real-world image dataset with quality issues is detaile…

cs.LG20193 cited

Deep Generative Models Strike Back! Improving Understanding and Evaluation in Light of Unmet Expectations for OoD Data

John Just, Sambuddha Ghosal

Advances in deep generative and density models have shown impressive capacity to model complex probability density functions in lower-dimensional space. Also, applying such models…

cs.CV2019

Mass Estimation from Images using Deep Neural Network and Sparse Ground Truth

Muhammad K A Hamdan, Daine T. Rover, Matthew J. Darr +1

Supervised learning is the workhorse for regression and classification tasks, but the standard approach presumes ground truth for every measurement. In real world applications, lim…