Learning from disagreement: A survey

AN Uma, T Fornaciari, D Hovy, S Paun, B Plank… - Journal of Artificial …, 2021 - jair.org
Abstract Many tasks in Natural Language Processing (NLP) and Computer Vision (CV) offer
evidence that humans disagree, from objective tasks such as part-of-speech tagging to more …

Overcoming limitations of mixture density networks: A sampling and fitting framework for multimodal future prediction

O Makansi, E Ilg, O Cicek… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Future prediction is a fundamental principle of intelligence that helps plan actions and avoid
possible dangers. As the future is uncertain to a large extent, modeling the uncertainty and …

Contactdb: Analyzing and predicting grasp contact via thermal imaging

S Brahmbhatt, C Ham, CC Kemp… - Proceedings of the …, 2019 - openaccess.thecvf.com
Gras** and manipulating objects is an important human skill. Since hand-object contact is
fundamental to gras**, capturing it can lead to important insights. However, observing …

Eliciting and learning with soft labels from every annotator

KM Collins, U Bhatt, A Weller - Proceedings of the AAAI conference on …, 2022 - ojs.aaai.org
The labels used to train machine learning (ML) models are of paramount importance.
Typically for ML classification tasks, datasets contain hard labels, yet learning using soft …

SemEval-2021 task 12: Learning with disagreements

A Uma, T Fornaciari, A Dumitrache… - Proceedings of the …, 2021 - aclanthology.org
Disagreement between coders is ubiquitous in virtually all datasets annotated with human
judgements in both natural language processing and computer vision. However, most …

Deep-panther: Learning-based perception-aware trajectory planner in dynamic environments

J Tordesillas, JP How - IEEE Robotics and Automation Letters, 2023 - ieeexplore.ieee.org
This letter presents Deep-PANTHER, a learning-based perception-aware trajectory planner
for unmanned aerial vehicles (UAVs) in dynamic environments. Given the current state of the …

Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing

D Perera, V Letzelter, T Mariotte… - Advances in neural …, 2025 - proceedings.neurips.cc
Abstract We introduce Annealed Multiple Choice Learning (aMCL) which combines
simulated annealing with MCL. MCL is a learning framework handling ambiguous tasks by …

Iteratively applying neural networks to automatically identify pixels of salient objects portrayed in digital images

IM Pao, Z Lin, S Stuckey, J Zhang, B Leong - US Patent 11,244,195, 2022 - Google Patents
The present disclosure relates to systems, method, and computer readable media that
iteratively apply a neural network to a digital image at a reduced resolution to auto matically …

Utilizing interactive deep learning to select objects in digital visual media

B Price, S Cohen, M Long, JH Liew - US Patent 11,568,627, 2023 - Google Patents
US11568627B2 - Utilizing interactive deep learning to select objects in digital visual media
- Google Patents US11568627B2 - Utilizing interactive deep learning to select objects in …

The visual centrifuge: Model-free layered video representations

JB Alayrac, J Carreira… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
True video understanding requires making sense of non-lambertian scenes where the color
of light arriving at the camera sensor encodes information about not just the last object it …