DeluluNet enables continued prediction under modality substitution, addition, or subsets by training a multi-modal model from a unimodal teacher and unlabeled multimodal data via modality hallucination.
Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Convolutional Neural Networks have achieved state-of-the-art performance on a wide range of tasks. Most benchmarks are led by ensembles of these powerful learners, but ensembling is typically treated as a post-hoc procedure implemented by averaging independently trained models with model variation induced by bagging or random initialization. In this paper, we rigorously treat ensembling as a first-class problem to explicitly address the question: what are the best strategies to create an ensemble? We first compare a large number of ensembling strategies, and then propose and evaluate novel strategies, such as parameter sharing (through a new family of models we call TreeNets) as well as training under ensemble-aware and diversity-encouraging losses. We demonstrate that TreeNets can improve ensemble performance and that diverse ensembles can be trained end-to-end under a unified loss, achieving significantly higher "oracle" accuracies than classical ensembles.
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
method 1polarities
use method 1representative citing papers
Conformalized Quantum DeepONet Ensembles reduce operator inference from quadratic to linear complexity using QOrthoNNs and SPQCs while delivering distribution-free uncertainty guarantees through ensemble conformal prediction.
Deep learning on information-rich scientific images collapses to one-dimensional predictions due to a mismatch between data priors and the model's simplicity bias, even after robustification techniques.
Extends DAE theory to POMDPs with minimal changes and introduces discrete latent dynamics to cut computational cost, with ALE experiments showing scalability and retained sample efficiency.
A multi-task network is introduced to generate narrow predictive intervals for counts in medical images while maintaining target coverage, tested on cell and white matter hyperintensity counting.
citing papers explorer
-
Conformalized Quantum DeepONet Ensembles for Scalable Operator Learning with Distribution-Free Uncertainty
Conformalized Quantum DeepONet Ensembles reduce operator inference from quadratic to linear complexity using QOrthoNNs and SPQCs while delivering distribution-free uncertainty guarantees through ensemble conformal prediction.
-
Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning
Extends DAE theory to POMDPs with minimal changes and introduces discrete latent dynamics to cut computational cost, with ALE experiments showing scalability and retained sample efficiency.