Stefan Duffner

Thibault Douzon, Stefan Duffner, Christophe Garcia et al.

Transformer-based Language Models are widely used in Natural Language Processing related tasks. Thanks to their pre-training, they have been successfully adapted to Information Extraction in business documents. However, most pre-training tasks proposed in the literature for business documents are too generic and not sufficient to learn more complex structures. In this paper, we use LayoutLM, a language model pre-trained on a collection of business documents, and introduce two new pre-training tasks that further improve its capacity to extract relevant information. The first is aimed at better understanding the complex layout of documents, and the second focuses on numeric values and their order of magnitude. These tasks force the model to learn better-contextualized representations of the scanned documents. We further introduce a new post-processing algorithm to decode BIESO tags in Information Extraction that performs better with complex entities. Our method significantly improves extraction performance on both public (from 93.88 to 95.50 F1 score) and private (from 84.35 to 84.84 F1 score) datasets composed of expense receipts, invoices, and purchase orders.

Thibault Douzon, Stefan Duffner, Christophe Garcia et al.

Since their release, Transformers have revolutionized many fields from Natural Language Understanding to Computer Vision. Document Understanding (DU) was not left behind with first Transformer based models for DU dating from late 2019. However, the computational complexity of the self-attention operation limits their capabilities to small sequences. In this paper we explore multiple strategies to apply Transformer based models to long multi-page documents. We introduce 2 new multi-modal (text + layout) long-range models for DU. They are based on efficient implementations of Transformers for long sequences. Long-range models can process whole documents at once effectively and are less impaired by the document's length. We compare them to LayoutLM, a classical Transformer adapted for DU and pre-trained on millions of documents. We further propose 2D relative attention bias to guide self-attention towards relevant tokens without harming model efficiency. We observe improvements on multi-page business documents on Information Retrieval for a small performance cost on smaller sequences. Relative 2D attention revealed to be effective on dense text for both normal and long-range models.

Matthis Manthe, Stefan Duffner, Carole Lartizien

Federated learning and its application to medical image segmentation have recently become a popular research topic. This training paradigm suffers from statistical heterogeneity between participating institutions' local datasets, incurring convergence slowdown as well as potential accuracy loss compared to classical training. To mitigate this effect, federated personalization emerged as the federated optimization of one model per institution. We propose a novel personalization algorithm tailored to the feature shift induced by the usage of different scanners and acquisition parameters by different institutions. This method is the first to account for both inter and intra-institution feature shift (multiple scanners used in a single institution). It is based on the computation, within each centre, of a series of radiomic features capturing the global texture of each 3D image volume, followed by a clustering analysis pooling all feature vectors transferred from the local institutions to the central server. Each computed clustered decentralized dataset (potentially including data from different institutions) then serves to finetune a global model obtained through classical federated learning. We validate our approach on the Federated Brain Tumor Segmentation 2022 Challenge dataset (FeTS2022). Our code is available at (https://github.com/MatthisManthe/radiomics_CFFL).

Aurélien Cecille, Stefan Duffner, Franck Davoine et al.

Monocular depth estimation has greatly improved in the recent years but models predicting metric depth still struggle to generalize across diverse camera poses and datasets. While recent supervised methods mitigate this issue by leveraging ground prior information at inference, their adaptability to self-supervised settings is limited due to the additional challenge of scale recovery. Addressing this gap, we propose in this paper a novel constraint on ground areas designed specifically for the self-supervised paradigm. This mechanism not only allows to accurately recover the scale but also ensures coherence between the depth prediction and the ground prior. Experimental results show that our method surpasses existing scale recovery techniques on the KITTI benchmark and significantly enhances model generalization capabilities. This improvement can be observed by its more robust performance across diverse camera rotations and its adaptability in zero-shot conditions with previously unseen driving datasets such as DDAD.

Charles De Lambilly, Stefan Duffner

This paper introduces Growing Networks with Autonomous Pruning (GNAP) for image classification. Unlike traditional convolutional neural networks, GNAP change their size, as well as the number of parameters they are using, during training, in order to best fit the data while trying to use as few parameters as possible. This is achieved through two complementary mechanisms: growth and pruning. GNAP start with few parameters, but their size is expanded periodically during training to add more expressive power each time the network has converged to a saturation point. Between these growing phases, model parameters are trained for classification and pruned simultaneously, with complete autonomy by gradient descent. Growing phases allow GNAP to improve their classification performance, while autonomous pruning allows them to keep as few parameters as possible. Experimental results on several image classification benchmarks show that our approach can train extremely sparse neural networks with high accuracy. For example, on MNIST, we achieved 99.44% accuracy with as few as 6.2k parameters, while on CIFAR10, we achieved 92.2\ accuracy with 157.8k parameters.

Martial Guidez, Stefan Duffner, Yannick Alpou et al.

Although deep neural networks and in particular Convolutional Neural Networks have demonstrated state-of-the-art performance in image classification with relatively high efficiency, they still exhibit high computational costs, often rendering them impractical for real-time and edge applications. Therefore, a multitude of compression techniques have been developed to reduce these costs while maintaining accuracy. In addition, dynamic architectures have been introduced to modulate the level of compression at execution time, which is a desirable property in many resource-limited application scenarios. The proposed method effectively integrates two well-established optimization techniques: early exits and knowledge distillation, where a reduced student early-exit model is trained from a more complex teacher early-exit model. The primary contribution of this research lies in the approach for training the student early-exit model. In comparison to the conventional Knowledge Distillation loss, our approach incorporates a new entropy-based loss for images where the teacher's classification was incorrect. The proposed method optimizes the trade-off between accuracy and efficiency, thereby achieving significant reductions in computational complexity without compromising classification performance. The validity of this approach is substantiated by experimental results on image classification datasets CIFAR10, CIFAR100 and SVHN, which further opens new research perspectives for Knowledge Distillation in other contexts.

Aurélien Cecille, Stefan Duffner, Franck Davoine et al.

Accurate monocular depth estimation is crucial for 3D scene understanding, but existing methods often blur depth at object boundaries, introducing spurious intermediate 3D points. While achieving sharp edges usually requires very fine-grained supervision, our method produces crisp depth discontinuities using only self-supervision. Specifically, we model per-pixel depth as a mixture distribution, capturing multiple plausible depths and shifting uncertainty from direct regression to the mixture weights. This formulation integrates seamlessly into existing pipelines via variance-aware loss functions and uncertainty propagation. Extensive evaluations on KITTI and VKITTIv2 show that our method achieves up to 35% higher boundary sharpness and improves point cloud quality compared to state-of-the-art baselines.

Luca Veyrin-Forrer, Ataollah Kamal, Stefan Duffner et al.

GNNs are powerful models based on node representation learning that perform particularly well in many machine learning problems related to graphs. The major obstacle to the deployment of GNNs is mostly a problem of societal acceptability and trustworthiness, properties which require making explicit the internal functioning of such models. Here, we propose to mine activation rules in the hidden layers to understand how the GNNs perceive the world. The problem is not to discover activation rules that are individually highly discriminating for an output of the model. Instead, the challenge is to provide a small set of rules that cover all input graphs. To this end, we introduce the subjective activation pattern domain. We define an effective and principled algorithm to enumerate activations rules in each hidden layer. The proposed approach for quantifying the interest of these rules is rooted in information theory and is able to account for background knowledge on the input graph data. The activation rules can then be redescribed thanks to pattern languages involving interpretable features. We show that the activation rules provide insights on the characteristics used by the GNN to classify the graphs. Especially, this allows to identify the hidden features built by the GNN through its different layers. Also, these rules can subsequently be used for explaining GNN decisions. Experiments on both synthetic and real-life datasets show highly competitive performance, with up to 200% improvement in fidelity on explaining graph classification over the SOTA methods.

Anthony Berthelier, Yongzhe Yan, Thierry Chateau et al.

While deep neural networks (DNNs) have proven to be efficient for numerous tasks, they come at a high memory and computation cost, thus making them impractical on resource-limited devices. However, these networks are known to contain a large number of parameters. Recent research has shown that their structure can be more compact without compromising their performance. In this paper, we present a sparsity-inducing regularization term based on the ratio l1/l2 pseudo-norm defined on the filter coefficients. By defining this pseudo-norm appropriately for the different filter kernels, and removing irrelevant filters, the number of kernels in each layer can be drastically reduced leading to very compact Deep Convolutional Neural Networks (DCNN) structures. Unlike numerous existing methods, our approach does not require an iterative retraining process and, using this regularization term, directly produces a sparse model during the training process. Furthermore, our approach is also much easier and simpler to implement than existing methods. Experimental results on MNIST and CIFAR-10 show that our approach significantly reduces the number of filters of classical models such as LeNet and VGG while reaching the same or even better accuracy than the baseline models. Moreover, the trade-off between the sparsity and the accuracy is compared to other loss regularization terms based on the l1 or l2 norm as well as the SSL, NISP and GAL methods and shows that our approach is outperforming them.

Yongzhe Yan, Stefan Duffner, Priyanka Phutane et al.

We present a facial landmark position correlation analysis as well as its applications. Although numerous facial landmark detection methods have been presented in the literature, few of them explicitly take into account the inherent relationship among landmarks. To reveal and interpret this relationship, we propose to analyze landmark correlation by using Canonical Correlation Analysis~(CCA). We experimentally show that the dense facial landmark annotations in current benchmarks are strongly correlated. We propose two applications based on this analysis. First, by analyzing the landmark correlation, we gain some interesting insights into the predictions of different landmark detection models (including random forests model and CNN models). We also demonstrate how CNNs progressively learn to predict facial landmarks. Second, we propose a few-shot learning method that allows to considerably reduce the manual effort for dense landmark annotation.

Yongzhe Yan, Stefan Duffner, Priyanka Phutane et al.

The recent performance of facial landmark detection has been significantly improved by using deep Convolutional Neural Networks (CNNs), especially the Heatmap Regression Models (HRMs). Although their performance on common benchmark datasets has reached a high level, the robustness of these models still remains a challenging problem in the practical use under noisy conditions of realistic environments. Contrary to most existing work focusing on the design of new models, we argue that improving the robustness requires rethinking many other aspects, including the use of datasets, the format of landmark annotation, the evaluation metric as well as the training and detection algorithm itself. In this paper, we propose a novel method for robust facial landmark detection, using a loss function based on the 2D Wasserstein distance combined with a new landmark coordinate sampling relying on the barycenter of the individual probability distributions. Our method can be plugged-and-play on most state-of-the-art HRMs with neither additional complexity nor structural modifications of the models. Further, with the large performance increase, we found that current evaluation metrics can no longer fully reflect the robustness of these models. Therefore, we propose several improvements to the standard evaluation protocol. Extensive experimental results on both traditional evaluation metrics and our evaluation metrics demonstrate that our approach significantly improves the robustness of state-of-the-art facial landmark detection models.

Paul Compagnon, Grégoire Lefebvre, Stefan Duffner et al.

Traditionally, the automatic recognition of human activities is performed with supervised learning algorithms on limited sets of specific activities. This work proposes to recognize recurrent activity patterns, called routines, instead of precisely defined activities. The modeling of routines is defined as a metric learning problem, and an architecture, called SS2S, based on sequence-to-sequence models is proposed to learn a distance between time series. This approach only relies on inertial data and is thus non intrusive and preserves privacy. Experimental results show that a clustering algorithm provided with the learned distance is able to recover daily routines.

Lilei Zheng, Ying Zhang, Stefan Duffner et al.

This paper presents a deep nonlinear metric learning framework for data visualization on an image dataset. We propose the Triangular Similarity and prove its equivalence to the Cosine Similarity in measuring a data pair. Based on this novel similarity, a geometrically motivated loss function - the triangular loss - is then developed for optimizing a metric learning system comprising two identical CNNs. It is shown that this deep nonlinear system can be efficiently trained by a hybrid algorithm based on the conventional backpropagation algorithm. More interestingly, benefiting from classical manifold learning theories, the proposed system offers two different views to visualize the outputs, the second of which provides better classification results than the state-of-the-art methods in the visualizable spaces.