Data to 13 Oct 2026

Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles

arXiv 1606.07839 ↗First posted 24 Jun 2016cs.CV cs.CLcited by 77

Not on the map. Why?

Abstract (arXiv)

Many practical perception systems exist within larger processes that include interactions with users or additional components capable of evaluating the quality of predicted solutions. In these contexts, it is beneficial to provide these oracle mechanisms with multiple highly likely hypotheses rather than a single prediction. In this work, we pose the task of producing multiple outputs as a learning problem over an ensemble of deep networks -- introducing a novel stochastic gradient descent based approach to minimize the loss with respect to an oracle. Our method is simple to implement, agnostic to both architecture and loss function, and parameter-free. Our approach achieves lower oracle error compared to existing methods on a wide range of tasks and deep architectures. We also show qualitatively that the diverse solutions produced often provide interpretable representations of task ambiguity.

Key facts. Cited by 77 papers in the map (data through 13 Oct 2026). First posted on arXiv 24 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 15; 2022: 11; 2023: 12; 2024: 15; 2025: 14; 2026: 10.

77 papers.

Sort:

By area:

2022Matryoshka Representation Learningcited by 274
2021MoViNets: Mobile Video Networks for Efficient Video Recognitioncited by 135
2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
2022Residual Mixture of Expertscited by 39
2024HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attentioncited by 38
2021Divide-and-Conquer for Lane-Aware Diverse Trajectory Predictioncited by 37
2021Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generationcited by 35
2021Diversity and Generalization in Neural Network Ensemblescited by 32
2021Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Groundingcited by 29
2021Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentationcited by 29
2022Bootstrap Motion Forecasting With Self-Consistent Constraintscited by 23
2021Using Soft Labels to Model Uncertainty in Medical Image Segmentationcited by 18

38 more

2021DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samplescited by 18
2022Verification-Aided Deep Ensemble Selectioncited by 18
2025Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSMcited by 18
2021Class-Incremental Experience Replay for Continual Learning under Concept Driftcited by 17
2022TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Predictioncited by 14
2023That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentationcited by 13
2023Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysiscited by 12
2024Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingcited by 12
2021MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminatorscited by 11
2023R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intentscited by 10
2025From Samples to Scenarios: A New Paradigm for Probabilistic Forecastingcited by 10
2023Laplacian Segmentation Networks Improve Epistemic Uncertainty Quantificationcited by 9
2023A Holistic Assessment of the Reliability of Machine Learning Systemscited by 9
2021Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Modelcited by 8
2023Diverse Multimedia Layout Generation with Multi Choice Learningcited by 8
2022MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Viewscited by 7
2022Self-Activating Neural Ensembles for Continual Reinforcement Learningcited by 7
2023Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Datacited by 7
2024ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode Modelingcited by 7
2023ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimationcited by 6
2024Winner-takes-all learners are geometry-aware conditional density estimatorscited by 6
2024FutureNet-LOF: Joint Trajectory Prediction and Lane Occupancy Field Prediction with Future Context Encodingcited by 6
2024Decoder ensembling for learned latent geometriescited by 6
2022SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficultycited by 5
2025MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learningcited by 5
2021Hypernet-Ensemble Learning of Segmentation Probability for Medical Image Segmentation with Ambiguous Labelscited by 4
2024Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecastingcited by 4
2024Hierarchical Uncertainty Exploration via Feedforward Posterior Treescited by 4
2024CryoSPIN: Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inferencecited by 4
2024Annealed Winner-Takes-All for Motion Forecastingcited by 4
2025CogAD: Cognitive-Hierarchy Guided End-to-End Autonomous Drivingcited by 4
2025Winner-takes-all for Multivariate Probabilistic Time Series Forecastingcited by 4
2026Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generationcited by 4
2023FFINet: Future Feedback Interaction Network for Motion Forecastingcited by 3
2024Multiple Choice Learning for Efficient Speech Separation with Many Speakerscited by 3
2025TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecastingcited by 3
2021Visual Attention in Imaginative Agentscited by 2
2022Multi-rater Prism: Learning self-calibrated medical image segmentation from multiple raterscited by 2

50 most cited of 77 All 77 (JSON)