Coupled Ensembles of Neural Networks

Dutt, Anuvabh; Pellerin, Denis; Quénot, Georges

doi:10.1109/cbmi.2018.8516453

Cited by 10 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be mentioned that an ensemble does not have to increase the cost of the computation time (training a CNN multiple times) [71]. Instead, the spirit of the ensemble can be realized at different levels, for instance, by multicolumn and multibranch architectures, where the training only needs to be carried out once [35], [72], [73]. Even with a single-branch architecture, an ensemble can be performed with a special training strategy that passes a range of local minima during the training process [74].…”

Section: Discussionmentioning

confidence: 99%

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Qiu

Tong

Schmitt

et al. 2020

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

View full text Add to dashboard Cite

As a unique classification scheme for urban forms and functions, the local climate zone (LCZ) system provides essential general information for any studies related to urban environments, especially on a large scale. Remote sensing data-based classification approaches are the key to large-scale mapping and monitoring of LCZs. The potential of deep learning-based approaches is not yet fully explored, even though advanced convolutional neural networks (CNNs) continue to push the frontiers for various computer vision tasks. One reason is that published studies are based on different datasets, usually at a regional scale, which makes it impossible to fairly and consistently compare the potential of different CNNs for real-world scenarios. This article is based on the big So2Sat LCZ42 benchmark dataset dedicated to LCZ classification. Using this dataset, we studied a range of CNNs of varying sizes. In addition, we proposed a CNN to classify LCZs from Sentinel-2 images, Sen2LCZ-Net. Using this base network, we propose fusing multilevel features using the extended Sen2LCZ-Net-MF. With this proposed simple network architecture, and the highly competitive benchmark dataset, we obtain results that are better than those obtained by the state-of-the-art CNNs, while requiring less computation with fewer layers and parameters. Large-scale LCZ classification examples of completely unseen areas are presented, demonstrating the potential of our proposed Sen2LCZ-Net-MF

show abstract

Section: Discussionmentioning

confidence: 99%

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Qiu

Tong

Schmitt

et al. 2020

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

View full text Add to dashboard Cite

show abstract

“…It uses three networks to learn robust facial expression features in the presence of noisy annotations. Inspired by [20,21,22], we use three networks with identical architecture, but different initialization, trained jointly using a convex combination of supervision loss and consistency loss. Different initialization promote different learning paths for the networks, though they have same architecture.…”

Section: Overviewmentioning

confidence: 99%

Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training

Gera,

Balasubramanian

2021

Preprint

View full text Add to dashboard Cite

Facial expression recognition (FER) in the wild is crucial for building reliable human-computer interactive systems. However, annotations of large scale datasets in FER has been a key challenge as these datasets suffer from noise due to various factors like crowd sourcing, subjectivity of annotators, poor quality of images, automatic labelling based on key word search etc. Such noisy annotations impede the performance of FER due to the memorization ability of deep networks. During early learning stage, deep networks fit on clean data. Then, eventually, they start overfitting on noisy labels due to their memorization ability, which limits FER performance. This report presents Consensual Collaborative Training (CCT) framework used in our submission to expression recognition track of the Affective Behaviour Analysis in-the-wild (ABAW) 2021 competition. CCT co-trains three networks jointly using a convex combination of supervision loss and consistency loss, without making any assumption about the noise distribution. A dynamic transition mechanism is used to move from supervision loss in early learning to consistency loss for consensus of predictions among networks in the later stage. Co-training reduces overall error, and consistency loss prevents overfitting to noisy samples. The performance of the model is validated on challenging Aff-Wild2 dataset for categorical expression classification. Our code is made publicly available 1 .

show abstract

“…Ensembles of neural networks are widely successful for improving both the accuracy and predictive uncertainty of very different predictive tasks, ranging from supervised learning [14] to few-shot learning [11]. Recent studies empirically show that deep ensembles can outperform single models with equivalent computational budgets on image classification tasks [10], [9], [13], [40]. We have in common with these works the outcome, i.e.…”

Section: Related Workmentioning

confidence: 99%

“…Indeed, [13] suggested the possibility of obtaining better performance with ensembles but without performing an extensive empirical evaluation with state-of-the-art architectures. [10] mainly focused their attention on the possible strategies to combine the predictions of the ensemble members. Differently from [9], we compare neural ensembles with single networks not only of the same depth but also of the same width and greater depth.…”

Section: Related Workmentioning

confidence: 99%

On the Effectiveness of Neural Ensembles for Image Classification with Small Datasets

Brigato¹,

Iocchi²

2021

Preprint

View full text Add to dashboard Cite

Deep neural networks represent the gold standard for image classification. However, they usually need large amounts of data to reach superior performance. In this work, we focus on image classification problems with a few labeled examples per class and improve data efficiency by using an ensemble of relatively small networks. For the first time, our work broadly studies the existing concept of neural ensembling in domains with small data, through extensive validation using popular datasets and architectures. We compare ensembles of networks to their deeper or wider single competitors given a total fixed computational budget. We show that ensembling relatively shallow networks is a simple yet effective technique that is generally better than current state-of-the-art approaches for learning from small datasets. Finally, we present our interpretation according to which neural ensembles are more sample efficient because they learn simpler functions.

show abstract

Coupled Ensembles of Neural Networks

Cited by 10 publications

References 13 publications

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training

On the Effectiveness of Neural Ensembles for Image Classification with Small Datasets

Contact Info

Product

Resources

About