Stéphane Pateux

Yuqing Hu, Stéphane Pateux, Vincent Gripon

Transductive Few-Shot learning has gained increased attention nowadays considering the cost of data annotations along with the increased accuracy provided by unlabelled samples in the domain of few shot. Especially in Few-Shot Classification (FSC), recent works explore the feature distributions aiming at maximizing likelihoods or posteriors with respect to the unknown parameters. Following this vein, and considering the parallel between FSC and clustering, we seek for better taking into account the uncertainty in estimation due to lack of data, as well as better statistical properties of the clusters associated with each class. Therefore in this paper we propose a new clustering method based on Variational Bayesian inference, further improved by Adaptive Dimension Reduction based on Probabilistic Linear Discriminant Analysis. Our proposed method significantly improves accuracy in the realistic unbalanced transductive setting on various Few-Shot benchmarks when applied to features used in previous studies, with a gain of up to $6\%$ in accuracy. In addition, when applied to balanced setting, we obtain very competitive results without making use of the class-balance artefact which is disputable for practical use cases. We also provide the performance of our method on a high performing pretrained backbone, with the reported results further surpassing the current state-of-the-art accuracy, suggesting the genericity of the proposed method.

Matthieu Gendrin, Stéphane Pateux, Théo Ladune

3D Gaussian Splatting (3DGS) is a major breakthrough in 3D scene reconstruction. With a number of views of a given object or scene, the algorithm trains a model composed of 3D gaussians, which enables the production of novel views from arbitrary points of view. This freedom of movement is referred to as 6DoF for 6 degrees of freedom: a view is produced for any position (3 degrees), orientation of camera (3 other degrees). On large scenes, though, the input views are acquired from a limited zone in space, and the reconstruction is valuable for novel views from the same zone, even if the scene itself is almost unlimited in size. We refer to this particular case as 3DoF+, meaning that the 3 degrees of freedom of camera position are limited to small offsets around the central position. Considering the problem of coordinate quantization, the impact of position error on the projection error in pixels is studied. It is shown that the projection error is proportional to the squared inverse distance of the point being projected. Consequently, a new quantization scheme based on spherical coordinates is proposed. Rate-distortion performance of the proposed method are illustrated on the well-known Garden scene.

Matthieu Gendrin, Stéphane Pateux, Xiaoran Jiang et al.

The quality of the camera calibration is of major importance for evaluating progresses in novel view synthesis, as a 1-pixel error on the calibration has a significant impact on the reconstruction quality. While there is no ground truth for real scenes, the quality of the calibration is assessed by the quality of the novel view synthesis. This paper proposes to use a 3DGS model to fine tune calibration by backpropagation of novel view color loss with respect to the cameras parameters. The new calibration alone brings an average improvement of 0.4 dB PSNR on the dataset used as reference by 3DGS. The fine tuning may be long and its suitability depends on the criticity of training time, but for calibration of reference scenes, such as Mip-NeRF 360, the stake of novel view quality is the most important.

Stéphane Pateux, Matthieu Gendrin, Luce Morin et al.

3D Gaussian Splatting (3DGS) proposes an efficient solution for novel view synthesis. Its framework provides fast and high-fidelity rendering. Although less complex than other solutions such as Neural Radiance Fields (NeRF), there are still some challenges building smaller models without sacrificing quality. In this study, we perform a careful analysis of 3DGS training process and propose a new optimization methodology. Our Better Optimized Gaussian Splatting (BOGausS) solution is able to generate models up to ten times lighter than the original 3DGS with no quality degradation, thus significantly boosting the performance of Gaussian Splatting compared to the state of the art.

Yassir Bendou, Yuqing Hu, Raphael Lafargue et al.

Few-shot learning aims at leveraging knowledge learned by one or more deep learning models, in order to obtain good classification performance on new problems, where only a few labeled samples per class are available. Recent years have seen a fair number of works in the field, introducing methods with numerous ingredients. A frequent problem, though, is the use of suboptimally trained models to extract knowledge, leading to interrogations on whether proposed approaches bring gains compared to using better initial models without the introduced ingredients. In this work, we propose a simple methodology, that reaches or even beats state of the art performance on multiple standardized benchmarks of the field, while adding almost no hyperparameters or parameters to those used for training the initial deep learning models on the generic dataset. This methodology offers a new baseline on which to propose (and fairly compare) new techniques or adapt existing ones.

Yuqing Hu, Vincent Gripon, Stéphane Pateux

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed with the common aim of transferring knowledge acquired on a previously solved task, what is often achieved by using a pretrained feature extractor. Following this vein, in this paper we propose a novel transfer-based method which aims at processing the feature vectors so that they become closer to Gaussian-like distributions, resulting in increased accuracy. In the case of transductive few-shot learning where unlabelled test samples are available during training, we also introduce an optimal-transport inspired algorithm to boost even further the achieved performance. Using standardized vision benchmarks, we show the ability of the proposed methodology to achieve state-of-the-art accuracy with various datasets, backbone architectures and few-shot settings.

Yuqing Hu, Vincent Gripon, Stéphane Pateux

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-shot classification, among which transfer-based methods have proved to achieve the best performance. Following this vein, in this paper we propose a novel transfer-based method that builds on two successive steps: 1) preprocessing the feature vectors so that they become closer to Gaussian-like distributions, and 2) leveraging this preprocessing using an optimal-transport inspired algorithm (in the case of transductive settings). Using standardized vision benchmarks, we prove the ability of the proposed methodology to achieve state-of-the-art accuracy with various datasets, backbone architectures and few-shot settings.

Yuqing Hu, Vincent Gripon, Stéphane Pateux

In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples. In this context, works have proposed to introduce Graph Neural Networks (GNNs) aiming at exploiting the information contained in other samples treated concurrently, what is commonly referred to as the transductive setting in the literature. These GNNs are trained all together with a backbone feature extractor. In this paper, we propose a new method that relies on graphs only to interpolate feature vectors instead, resulting in a transductive learning setting with no additional parameters to train. Our proposed method thus exploits two levels of information: a) transfer features obtained on generic datasets, b) transductive information obtained from other samples to be classified. Using standard few-shot vision classification datasets, we demonstrate its ability to bring significant gains compared to other works.

Valentin Vielzeuf, Alexis Lechervy, Stéphane Pateux et al.

This paper proposes a step toward obtaining general models of knowledge for facial analysis, by addressing the question of multi-source transfer learning. More precisely, the proposed approach consists in two successive training steps: the first one consists in applying a combination operator to define a common embedding for the multiple sources materialized by different existing trained models. The proposed operator relies on an auto-encoder, trained on a large dataset, efficient both in terms of compression ratio and transfer learning performance. In a second step we exploit a distillation approach to obtain a lightweight student model mimicking the collection of the fused existing models. This model outperforms its teacher on novel tasks, achieving results on par with state-of-the-art methods on 15 facial analysis tasks (and domains), at an affordable training cost. Moreover, this student has 75 times less parameters than the original teacher and can be applied to a variety of novel face-related tasks.

Juan-Manuel Pérez-Rúa, Valentin Vielzeuf, Stéphane Pateux et al.

We tackle the problem of finding good architectures for multimodal classification problems. We propose a novel and generic search space that spans a large number of possible fusion architectures. In order to find an optimal architecture for a given dataset in the proposed search space, we leverage an efficient sequential model-based exploration approach that is tailored for the problem. We demonstrate the value of posing multimodal fusion as a neural architecture search problem by extensive experimentation on a toy dataset and two other real multimodal datasets. We discover fusion architectures that exhibit state-of-the-art performance for problems with different domain and dataset size, including the NTU RGB+D dataset, the largest multi-modal action recognition dataset available.

Valentin Vielzeuf, Alexis Lechervy, Stéphane Pateux et al.

In the context of deep learning, this article presents an original deep network, namely CentralNet, for the fusion of information coming from different sensors. This approach is designed to efficiently and automatically balance the trade-off between early and late fusion (i.e. between the fusion of low-level vs high-level information). More specifically, at each level of abstraction-the different levels of deep networks-uni-modal representations of the data are fed to a central neural network which combines them into a common embedding. In addition, a multi-objective regularization is also introduced, helping to both optimize the central network and the unimodal networks. Experiments on four multimodal datasets not only show state-of-the-art performance, but also demonstrate that CentralNet can actually choose the best possible fusion strategy for a given problem.

Valentin Vielzeuf, Corentin Kervadec, Stéphane Pateux et al.

This paper presents a novel approach to the facial expression generation problem. Building upon the assumption of the psychological community that emotion is intrinsically continuous, we first design our own continuous emotion representation with a 3-dimensional latent space issued from a neural network trained on discrete emotion classification. The so-obtained representation can be used to annotate large in the wild datasets and later used to trained a Generative Adversarial Network. We first show that our model is able to map back to discrete emotion classes with a objectively and subjectively better quality of the images than usual discrete approaches. But also that we are able to pave the larger space of possible facial expressions, generating the many moods of emotion. Moreover, two axis in this space may be found to generate similar expression changes as in traditional continuous representations such as arousal-valence. Finally we show from visual interpretation, that the third remaining dimension is highly related to the well-known dominance dimension from psychology.

Valentin Vielzeuf, Alexis Lechervy, Stéphane Pateux et al.

This paper proposes a novel multimodal fusion approach, aiming to produce best possible decisions by integrating information coming from multiple media. While most of the past multimodal approaches either work by projecting the features of different modalities into the same space, or by coordinating the representations of each modality through the use of constraints, our approach borrows from both visions. More specifically, assuming each modality can be processed by a separated deep convolutional network, allowing to take decisions independently from each modality, we introduce a central network linking the modality specific networks. This central network not only provides a common feature embedding but also regularizes the modality specific networks through the use of multi-task learning. The proposed approach is validated on 4 different computer vision tasks on which it consistently improves the accuracy of existing multimodal fusion approaches.

Valentin Vielzeuf, Corentin Kervadec, Stéphane Pateux et al.

This paper presents a light-weight and accurate deep neural model for audiovisual emotion recognition. To design this model, the authors followed a philosophy of simplicity, drastically limiting the number of parameters to learn from the target datasets, always choosing the simplest earning methods: i) transfer learning and low-dimensional space embedding allows to reduce the dimensionality of the representations. ii) The isual temporal information is handled by a simple score-per-frame selection process, averaged across time. iii) A simple frame selection echanism is also proposed to weight the images of a sequence. iv) The fusion of the different modalities is performed at prediction level (late usion). We also highlight the inherent challenges of the AFEW dataset and the difficulty of model selection with as few as 383 validation equences. The proposed real-time emotion classifier achieved a state-of-the-art accuracy of 60.64 % on the test set of AFEW, and ranked 4th at he Emotion in the Wild 2018 challenge.

Corentin Kervadec, Valentin Vielzeuf, Stéphane Pateux et al.

Numerous models describing the human emotional states have been built by the psychology community. Alongside, Deep Neural Networks (DNN) are reaching excellent performances and are becoming interesting features extraction tools in many computer vision tasks.Inspired by works from the psychology community, we first study the link between the compact two-dimensional representation of the emotion known as arousal-valence, and discrete emotion classes (e.g. anger, happiness, sadness, etc.) used in the computer vision community. It enables to assess the benefits -- in terms of discrete emotion inference -- of adding an extra dimension to arousal-valence (usually named dominance). Building on these observations, we propose CAKE, a 3-dimensional representation of emotion learned in a multi-domain fashion, achieving accurate emotion recognition on several public datasets. Moreover, we visualize how emotions boundaries are organized inside DNN representations and show that DNNs are implicitly learning arousal-valence-like descriptions of emotions. Finally, we use the CAKE representation to compare the quality of the annotations of different public datasets.

Valentin Vielzeuf, Stéphane Pateux, Frédéric Jurie

This paper addresses the question of emotion classification. The task consists in predicting emotion labels (taken among a set of possible labels) best describing the emotions contained in short video clips. Building on a standard framework -- lying in describing videos by audio and visual features used by a supervised classifier to infer the labels -- this paper investigates several novel directions. First of all, improved face descriptors based on 2D and 3D Convo-lutional Neural Networks are proposed. Second, the paper explores several fusion methods, temporal and multimodal, including a novel hierarchical method combining features and scores. In addition, we carefully reviewed the different stages of the pipeline and designed a CNN architecture adapted to the task; this is important as the size of the training set is small compared to the difficulty of the problem, making generalization difficult. The so-obtained model ranked 4th at the 2017 Emotion in the Wild challenge with the accuracy of 58.8 %.