Abstract: Multimodal representations and continual learning are two areas closely related to human intelligence. The former considers the learning of shared representation spaces where information from different modalities can be compared and integrated (we focus on cross-modal retrieval between language and visual representations). The latter studies how to prevent forgetting a previously learned task when learning a new one. While humans excel in these two aspects, deep neural networks are still quite limited. In this paper, we propose a combination of both problems into a continual cross-modal retrieval setting, where we study how the catastrophic interference caused by new tasks impacts the embedding spaces and their cross-modal alignment required for effective retrieval. We propose a general framework that decouples the training, indexing and querying stages. We also identify and study different factors that may lead to forgetting, and propose tools to alleviate it. We found that the indexing stage pays an important role and that simply avoiding reindexing the database with updated embedding networks can lead to significant gains. We evaluated our methods in two image-text retrieval datasets, obtaining significant gains with respect to the fine tuning baseline.

Abstract: Deep learning methods show great promise in a range of settings including the biomedical field. Explainability of these models is important in these fields for building end-user trust and to facilitate their confident deployment. Although several Machine Learning Interpretability tools have been proposed so far, there is currently no recognized evaluation standard to transfer the explainability results into a quantitative score. Several measures have been proposed as proxies for quantitative assessment of explainability methods. However, the robustness of the list of significant features provided by the explainability methods has not been addressed. In this work, we propose a new proxy for assessing the robustness of the list of significant features provided by two explainability methods. Our validation is defined at functionality-grounded level based on the ranked correlation statistical index and demonstrates its successful application in the framework of brain aging estimation. We assessed our proxy to estimate brain age using neuroscience data. Our results indicate small variability and high robustness in the considered explainability methods using this new proxy.

Abstract: The issue of ethnic bias has proven to affect the performance of face recognition in previous works, while it still remains to be vacant in face anti-spoofing. Therefore, in order to study the ethnic bias for face anti-spoofing, we introduce the largest CASIA-SURF Cross-ethnicity Face Anti-spoofing (CeFA) dataset, covering 3 ethnicities, 3 modalities, 1,607 subjects, and 2D plus 3D attack types. Five protocols are introduced to measure the affect under varied evaluation conditions, such as cross-ethnicity, unknown spoofs or both of them. As our knowledge, CASIA-SURF CeFA is the first dataset including explicit ethnic labels in current released datasets. Then, we propose a novel multi-modal fusion method as a strong baseline to alleviate the ethnic bias, which employs a partially shared fusion strategy to learn complementary information from multiple modalities. Extensive experiments have been conducted on the proposed dataset to verify its significance and generalization capability for other existing datasets, i.e., CASIA-SURF, OULU-NPU and SiW datasets. The dataset is available at https://sites.google.com/qq.com/face-anti-spoofing/welcome/challengecvpr2020?authuser=0.

Abstract: Differently from the regular classification task, in ordinal classification there is an order in the classes. As a consequence not all classification errors matter the same: a predicted class close to the groundtruth one is better than predicting a farther away class. To account for this, most previous works employ loss functions based on the absolute difference between the predicted and groundtruth class labels. We argue that there are many cases in ordinal classification where label values are arbitrary (for instance 1. . . C, being C the number of classes) and thus such loss functions may not be the best choice. We instead propose a network architecture that produces not a single class prediction but an ordered vector, or ranking, of all the possible classes from most to least likely. This is thanks to a loss function that compares groundtruth and predicted rankings of these class labels, not the labels themselves. Another advantage of this new formulation is that we can enforce consistency in the predictions, namely, predicted rankings come from some unimodal vector of scores with mode at the groundtruth class. We compare with the state of the art ordinal classification methods, showing
that ours attains equal or better performance, as measured by common ordinal classification metrics, on three benchmark datasets. Furthermore, it is also suitable for a new task on image aesthetics assessment, i.e. most voted score prediction. Finally, we also apply it to building damage assessment from satellite images, providing an analysis of its performance depending on the degree of imbalance of the dataset.

Abstract: In this paper, we propose a new approach to under-stand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels. At the frame level, we use a region-based approach that takes as input a primary region roughly corresponding to the user hands and a set of secondary regions potentially corresponding to the interacting objects and calculates the action score through a CNN formulation. This information is then fed to a Hierarchical LongShort-Term Memory Network (HLSTM) that captures temporal dependencies between actions within and across shots. Ablation studies thoroughly validate the proposed approach, showing in particular that both levels of the HLSTM architecture contribute to performance improvement. Furthermore, quantitative comparisons show that the proposed approach outperforms the state-of-the-art in terms of action recognition on standard benchmarks,without relying on motion information

Abstract: This paper summarizes the top contributions to the first challenge on thermal image super-resolution (TISR), which was organized as part of the Perception Beyond the Visible Spectrum (PBVS) 2020 workshop. In this challenge, a novel thermal image dataset is considered together with state-of-the-art approaches evaluated under a common framework. The dataset used in the challenge consists of 1021 thermal images, obtained from three distinct thermal cameras at different resolutions (low-resolution, mid-resolution, and high-resolution), resulting in a total of 3063 thermal images. From each resolution, 951 images are used for training and 50 for testing while the 20 remaining images are used for two proposed evaluations. The first evaluation consists of downsampling the low-resolution, mid-resolution, and high-resolution thermal images by x2, x3 and x4 respectively, and comparing their super-resolution results with the corresponding ground truth images. The second evaluation is comprised of obtaining the x2 super-resolution from a given mid-resolution thermal image and comparing it with the corresponding semi-registered high-resolution thermal image. Out of 51 registered participants, 6 teams reached the final validation phase.

Abstract: In this work we target the problem of hate speech detection in multimodal publications formed by a text and an image. We gather and annotate a large scale dataset from Twitter, MMHS150K, and propose different models that jointly analyze textual and visual information for hate speech detection, comparing them with unimodal detection. We provide quantitative and qualitative results and analyze the challenges of the proposed task. We find that, even though images are useful for the hate speech detection task, current multimodal models cannot outperform models analyzing only text. We discuss why and open the field and the dataset for further research.