UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation

Tian, Junjiao; Cheung, Wesley; Glaser, Nathaniel; Liu, Yen‐Cheng; Kira, Zsolt

doi:10.1109/icra40945.2020.9197266

Cited by 19 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, there are studies that integrate decisions from different sources through learnable models [63], [64], [65], [66]. Recently, confidence-based fusion has attracted attention [67], [68]. The significant difference between our method and them is that ours is an end-to-end fusion framework with theoretical guarantees.…”

Section: Related Workmentioning

confidence: 99%

Trusted Multi-View Classification with Dynamic Evidential Fusion

Han¹,

Zhang²,

Fu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations for follow-up tasks. Although effective, it is also crucial to ensure the reliability of both the multi-view integration and the final decision, especially for noisy, corrupted and out-of-distribution data. Dynamically assessing the trustworthiness of each view for different samples could provide reliable integration. This can be achieved through uncertainty estimation. With this in mind, we propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC), providing a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed TMC can promote classification reliability by considering evidence from each view. Specifically, we introduce the variational Dirichlet to characterize the distribution of the class probabilities, parameterized with evidence from different views and integrated with the Dempster-Shafer theory. The unified learning framework induces accurate uncertainty and accordingly endows the model with both reliability and robustness against possible noise or corruption. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness.

show abstract

Section: Related Workmentioning

confidence: 99%

Trusted Multi-View Classification with Dynamic Evidential Fusion

Han¹,

Zhang²,

Fu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, we can alternatively learn the class conditional likelihood f s (X|Y ) on the training data by the technique of Balanced-SoftMax, which has been widely applied on longtailed classification tasks [17], [49]. Specifically, for a data point (x j , y j ) at client i, the log-loss is calculated by…”

Section: Prior-corrected Bayes Classifiermentioning

confidence: 99%

Stabilizing and Improving Federated Learning with Non-IID Data and Client Dropout

Xu¹,

Yang²,

Ding³

et al. 2023

Preprint

View full text Add to dashboard Cite

The label distribution skew induced data heterogeniety has been shown to be a significant obstacle that limits the model performance in federated learning, which is particularly developed for collaborative model training over decentralized data sources while preserving user privacy. This challenge could be more serious when the participating clients are in unstable circumstances and dropout frequently. Previous work and our empirical observations demonstrate that the classifier head for classification task is more sensitive to label skew and the unstable performance of FedAvg mainly lies in the imbalanced training samples across different classes. The biased classifier head will also impact the learning of feature representations. Therefore, maintaining a balanced classifier head is of significant importance for building a better global model. To this end, we propose a simple yet effective framework by introducing a prior-calibrated softmax function for computing the cross-entropy loss and a prototype-based feature augmentation scheme to re-balance the local training, which are lightweight for edge devices and can facilitate the global model aggregation. The improved model performance over existing baselines in the presence of non-IID data and client dropout is demonstrated by conducting extensive experiments on benchmark classification tasks.

show abstract

“…Tian et al [55] showed that different uncertainty measures correlate differently to different types of sensory data degradation, and proposed a method to combine multiple types of uncertainties in an adaptive fusion scheme for unseen degradation with application to RGB-D semantic segmentation.…”

Section: ) Uncertainty Estimationmentioning

confidence: 99%

Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends

2021

View full text Add to dashboard Cite

As deep learning continues to dominate all state-of-the-art computer vision tasks, it is increasingly becoming an essential building block for robotic perception. This raises important questions concerning the safety and reliability of learning-based perception systems. There is an established field that studies safety certification and convergence guarantees of complex software systems at design-time. However, the unknown future deployment environments of an autonomous system and the complexity of learning-based perception make the generalization of design-time verification to run-time problematic. In the face of this challenge, more attention is starting to focus on run-time monitoring of performance and reliability of perception systems with several trends emerging in the literature in the face of this challenge. This paper attempts to identify these trends and summarise the various approaches to the topic.

show abstract

UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation

Cited by 19 publications

References 10 publications

Trusted Multi-View Classification with Dynamic Evidential Fusion

Trusted Multi-View Classification with Dynamic Evidential Fusion

Stabilizing and Improving Federated Learning with Non-IID Data and Client Dropout

Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends

Contact Info

Product

Resources

About