Evidential Reasoning for Ship Classification: Fusion of Deep Learning Classifiers

Debaque, Benoît; Florea, Mihai; Duclos-Hindie, Nicolas; Boury-Brisset, Anne-Claire

doi:10.23919/fusion43075.2019.9011296

Cited by 4 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OA Kappa EDLS [89] 0.8520 0.6298 ETMC [91] 0.9621 0.9042 EDLU [90] (γ = 0.4) 0.9765 0.9417 EDLU [90] (γ = 0.6) 0.9765 0.9417 EDLU [90] (γ = 0.8) 0.9783 0.9462 Proposed (SwinTransV2-T) 0.9964 0.9910 F. Ablation studies 1) Ablation study on each fusion stage: Firstly, we present the effects of each fusion stage. Fig.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Evidential Remote Sensing Landslide Image Classification With a New Divergence, Multiscale Saliency and an Improved Three-Branched Fusion

Zhang,

Cui,

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Hitherto, image-level classification on remote sensing landslide images has been paid attention to, but the accuracy of traditional deep learning-based methods still have room for improvement. The evidence theory is found efficient to boost the accuracy of neural networks, however, the present study argues three challenges that hinder the lead-in of this theory in deep landslide image classification. Aiming at the three problems, this study makes three improvements. For the interpretability and decision-invariance losses of three previous divergences, we propose a Belief Jensen-Renyi divergence with properties proven. To couple the evidence theory with deep remote sensing landslide image classification, a channel-wise multi-scale visual saliency fusion is developed. We additionally find that the channel-wise fusion is capable to reduce false recognition of networks as compared with original RGB images. To avoid decision failures in evidence-theoretic fusion process, we design an interpretability improved three-branched fusion. Experiments on Bijie Landslide dataset corroborate the synergistic benefits of the three improvements, where the proposal is compared with state-ofthe-art image classification backbone networks, remote sensing image scene classifiers, evidence fusion algorithms and versatile evidence-theoretic deep learning classifiers. We also evaluated the new method with two sort of image degradation, as well as an actual scenario in Luding County, China whose data is publicly available. The source code is at https://github.com/defzhangaa/ deeplandslideDS.

show abstract

Section: Methodsmentioning

confidence: 99%

“…In [89], dynamic evidence fusion is connected with trusted multi-view classification. Literature [91] presents a deep evidence-theoretic frame for accurate sheep classification. Then this study fairly compares them in the deep image-level classification task on remote sensing landslide images.…”

Section: Comparison Algorithmsmentioning

confidence: 99%

Deep Evidential Remote Sensing Landslide Image Classification With a New Divergence, Multiscale Saliency and an Improved Three-Branched Fusion

Zhang,

Cui,

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The same authors also propose a new multisensor benchmark dataset for detection and tracking. 22 The approach developed by Debaque et al 23 combines several DL classifiers using evidential reasoning based on Dempster-Shafer theory, to better take into account the uncertainty at the last layer of the models. They compare their approach to a baseline Bayesian classifier.…”

Section: Related Workmentioning

confidence: 99%

EO and radar fusion for fine-grained target classification with a strong few-shot learning baseline

Ballan,

Melo,

van den Broek

et al. 2024

Signal Processing, Sensor/Information Fusion, and Target Recognition XXXIII

View full text Add to dashboard Cite

Combining data from multiple sensors to improve the overall robustness and reliability of a classification system has become crucial in many applications, from military surveillance and decision support, to autonomous driving, robotics, and medical imaging. This so-called sensor fusion is especially interesting for fine-grained target classification, in which very specific sub-categories (e.g. ship types) need to be distinguished, a task that can be challenging with data from a single modality. Typical modalities are electro-optical (EO) image sensors, that can provide rich visual details of an object of interest, and radar, that can yield additional spatial information. Defined by the approach used to combine data from these sensors, several fusion techniques exist. For example, late fusion can merge class probabilities outputted by separate processing pipelines dedicated to each of the individual sensor data. In particular, deep learning (DL) has been widely leveraged for EO image analysis, but typically requires a lot of data to adapt to the nuances of a fine-grained classification task. Recent advances in DL on foundation models have shown a high potential when dealing with in-domain data scarcity, especially in combination with few-shot learning. This paper presents a framework to effectively combine EO and radar sensor data, and shows how this method outperforms stand-alone single sensor methods for fine-grained target classification. We adopt a strong few-shot image classification baseline based on foundation models, which robustly handles the lack of in-domain data and exploits rich visual features. In addition, we investigate a weighted and a Bayesian fusion approach to combine target class probabilities outputted by the image classification model and radar kinematic features. Experiments with data acquired in a measurement campaign at the port of Rotterdam show that our fusion method improves on the classification performance of individual modalities.

show abstract

Vessel classification for naval operations

Hollander

Rooij

Broek

et al. 2021

Artificial Intelligence and Machine Learning in Defense Applications III

View full text Add to dashboard Cite

Evidential Reasoning for Ship Classification: Fusion of Deep Learning Classifiers

Cited by 4 publications

References 24 publications

Deep Evidential Remote Sensing Landslide Image Classification With a New Divergence, Multiscale Saliency and an Improved Three-Branched Fusion

Deep Evidential Remote Sensing Landslide Image Classification With a New Divergence, Multiscale Saliency and an Improved Three-Branched Fusion

EO and radar fusion for fine-grained target classification with a strong few-shot learning baseline

Vessel classification for naval operations

Contact Info

Product

Resources

About