Self-Supervised Curricular Deep Learning for Chest X-Ray Image Classification

Deep learning technologies have already demonstrated a high potential to build diagnosis support systems from medical imaging data, such as Chest X-Ray images. However, the shortage of labeled data in the medical field represents one key obstacle to narrow down the performance gap with respect to applications in other image domains. In this work, we investigate the benefits of a curricular Self-Supervised Learning (SSL) pretraining scheme with respect to fully-supervised training regimes for pneumonia recognition on Chest X-Ray images of Covid-19 patients. We show that curricular SSL pretraining, which leverages unlabeled data, outperforms models trained from scratch, or pretrained on ImageNet, indicating the potential of performance gains by SSL pretraining on massive unlabeled datasets. Finally, we demonstrate that top-performing SSLpretrained models show a higher degree of attention in the lung regions, embodying models that may be more robust to possible external confounding factors in the training datasets, identified by previous works.

A study on the distribution of social biases in self-supervised learning visual models

Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorporated in the training data. These include operational biases, such as ineffective or uneven data sampling, but also ethical concerns, as the social biases are implicitly present\textemdash even inadvertently, in the training data or explicitly defined in unfair training schedules. In tasks having impact on human processes, the learning of social biases may produce discriminatory, unethical and untrustworthy consequences. It is often assumed that social biases stem from supervised learning on labelled data, and thus, Self-Supervised Learning (SSL) wrongly appears as an efficient and bias-free solution, as it does not require labelled data. However, it was recently proven that a popular SSL method also incorporates biases. In this paper, we study the biases of a varied set of SSL visual models, trained using ImageNet data, using a method and dataset designed by psychological experts to measure social biases. We show that there is a correlation between the type of the SSL model and the number of biases that it incorporates. Furthermore, the results also suggest that this number does not strictly depend on the model's accuracy and changes throughout the network. Finally, we conclude that a careful SSL model selection process can reduce the number of social biases in the deployed model, whilst keeping high performance.

Graph Neural Networks for Cross-Camera Data Association

Cross-camera image data association is essential for many multi-camera computer vision tasks, such as multi-camera pedestrian detection, multi-camera multi-target tracking, 3D pose estimation, etc. This association task is typically stated as a bipartite graph matching problem and often solved by applying minimum-cost flow techniques, which may be computationally inefficient with large data. Furthermore, cameras are usually treated by pairs, obtaining local solutions, rather than finding a global solution at once. Other key issue is that of the affinity measurement: the widespread usage of non-learnable pre-defined distances, such as the Euclidean and Cosine ones. This paper proposes an efficient approach for cross-cameras data-association focused on a global solution, instead of processing cameras by pairs. To avoid the usage of fixed distances, we leverage the connectivity of Graph Neural Networks, previously unused in this scope, using a Message Passing Network to jointly learn features and similarity. We validate the proposal for pedestrian multi-view association, showing results over the EPFL multi-camera pedestrian dataset. Our approach considerably outperforms the literature data association techniques, without requiring to be trained in the same scenario in which it is tested. Our code is available at \url{http://www-vpu.eps.uam.es/publications/gnn_cca}.

Improved skin lesion recognition by a Self-Supervised Curricular Deep Learning approach

State-of-the-art deep learning approaches for skin lesion recognition often require pretraining on larger and more varied datasets, to overcome the generalization limitations derived from the reduced size of the skin lesion imaging datasets. ImageNet is often used as the pretraining dataset, but its transferring potential is hindered by the domain gap between the source dataset and the target dermatoscopic scenario. In this work, we introduce a novel pretraining approach that sequentially trains a series of Self-Supervised Learning pretext tasks and only requires the unlabeled skin lesion imaging data. We present a simple methodology to establish an ordering that defines a pretext task curriculum. For the multi-class skin lesion classification problem, and ISIC-2019 dataset, we provide experimental evidence showing that: i) a model pretrained by a curriculum of pretext tasks outperforms models pretrained by individual pretext tasks, and ii) a model pretrained by the optimal pretext task curriculum outperforms a model pretrained on ImageNet. We demonstrate that this performance gain is related to the fact that the curriculum of pretext tasks better focuses the attention of the final model on the skin lesion. Beyond performance improvement, this strategy allows for a large reduction in the training time with respect to ImageNet pretraining, which is especially advantageous for network architectures tailored for a specific problem.

FVV Live: A real-time free-viewpoint video system with consumer electronics hardware

FVV Live is a novel end-to-end free-viewpoint video system, designed for low cost and real-time operation, based on off-the-shelf components. The system has been designed to yield high-quality free-viewpoint video using consumer-grade cameras and hardware, which enables low deployment costs and easy installation for immersive event-broadcasting or videoconferencing. The paper describes the architecture of the system, including acquisition and encoding of multiview plus depth data in several capture servers and virtual view synthesis on an edge server. All the blocks of the system have been designed to overcome the limitations imposed by hardware and network, which impact directly on the accuracy of depth data and thus on the quality of virtual view synthesis. The design of FVV Live allows for an arbitrary number of cameras and capture servers, and the results presented in this paper correspond to an implementation with nine stereo-based depth cameras. FVV Live presents low motion-to-photon and end-to-end delays, which enables seamless free-viewpoint navigation and bilateral immersive communications. Moreover, the visual quality of FVV Live has been assessed through subjective assessment with satisfactory results, and additional comparative tests show that it is preferred over state-of-the-art DIBR alternatives.

FVV Live: Real-Time, Low-Cost, Free Viewpoint Video

FVV Live is a novel real-time, low-latency, end-to-end free viewpoint system including capture, transmission, synthesis on an edge server and visualization and control on a mobile terminal. The system has been specially designed for low-cost and real-time operation, only using off-the-shelf components.

Semantic Driven Multi-Camera Pedestrian Detection

Nowadays, pedestrian detection is one of the pivotal fields in computer vision, especially when performed over video surveillance scenarios. People detection methods are highly sensitive to occlusions among pedestrians, which dramatically degrades performance in crowded scenarios. The cutback in camera prices has allowed generalizing multi-camera set-ups, which can better confront occlusions by using different points of view to disambiguate detections. In this paper we present an approach to improve the performance of these multi-camera systems and to make them independent of the considered scenario, via an automatic understanding of the scene content. This semantic information, obtained from a semantic segmentation, is used 1) to automatically generate a common Area of Interest for all cameras, instead of the usual manual definition of this area; and 2) to improve the 2D detections of each camera via an optimization technique which maximizes coherence of every detection both in all 2D views and in the 3D world, obtaining best-fitted bounding boxes and a consensus height for every pedestrian. Experimental results on five publicly available datasets show that the proposed approach, which does not require any training stage, outperforms state-of-the-art multi-camera pedestrian detectors non specifically trained for these datasets, which demonstrates the expected semantic-based robustness to different scenarios.