Federico Milani

The application of Deep Neural Networks (DNNs) to a broad variety of tasks demands methods for coping with the complex and opaque nature of these architectures. When a gold standard is available, performance assessment treats the DNN as a black box and computes standard metrics based on the comparison of the predictions with the ground truth. A deeper understanding of performances requires going beyond such evaluation metrics to diagnose the model behavior and the prediction errors. This goal can be pursued in two complementary ways. On one side, model interpretation techniques "open the box" and assess the relationship between the input, the inner layers and the output, so as to identify the architecture modules most likely to cause the performance loss. On the other hand, black-box error diagnosis techniques study the correlation between the model response and some properties of the input not used for training, so as to identify the features of the inputs that make the model fail. Both approaches give hints on how to improve the architecture and/or the training process. This paper focuses on the application of DNNs to Computer Vision (CV) tasks and presents a survey of the tools that support the black-box performance diagnosis paradigm. It illustrates the features and gaps of the current proposals, discusses the relevant research directions and provides a brief overview of the diagnosis tools in sectors other than CV.

The rapid development of remote sensing technologies and the availability of many satellite and aerial sensors have boosted the collection of large volumes of high-resolution images, promoting progress in a wide range of applications. As a consequence, Object detection (OD) in aerial images has gained much interest in the last few years. However, the development of object detectors requires a massive amount of carefully labeled data. Since annotating datasets is very time-consuming and may require expert knowledge, a consistent number of weakly supervised object localization (WSOL) and detection (WSOD) methods have been developed. These approaches exploit only coarse-grained metadata, typically whole image labels, to train object detectors. However, many challenges remain open due to the missing location information in the training process of WSOD approaches and to the complexity of remote sensing images. Furthermore, methods studied for natural images may not be directly applicable to remote sensing images (RSI) and may require carefully designed adaptations. This work provides a comprehensive survey of the recent achievements of remote sensing weakly supervised object detection (RSWSOD). An analysis of the challenges related to RSWSOD is presented, the advanced techniques developed to improve WSOD are summarized, the available benchmarking datasets are described and a discussion of future directions of RSWSOD research is provided.

Object Detection requires many precise annotations, which are available for natural images but not for many non-natural data sets such as artworks data sets. A solution is using Weakly Supervised Object Detection (WSOD) techniques that learn accurate object localization from image-level labels. Studies have demonstrated that state-of-the-art end-to-end architectures may not be suitable for domains in which images or classes sensibly differ from those used to pre-train networks. This paper presents a novel two-stage Weakly Supervised Object Detection approach for obtaining accurate bounding boxes on non-natural data sets. The proposed method exploits existing classification knowledge to generate pseudo-ground truth bounding boxes from Class Activation Maps (CAMs). The automatically generated annotations are used to train a robust Faster R-CNN object detector. Quantitative and qualitative analysis shows that bounding boxes generated from CAMs can compensate for the lack of manually annotated ground truth (GT) and that an object detector, trained with such pseudo-GT, surpasses end-to-end WSOD state-of-the-art methods on ArtDL 2.0 (≈41.5% mAP) and IconArt (≈17% mAP), two artworks data sets. The proposed solution is a step towards the computer-aided study of non-natural images and opens the way to more advanced tasks, e.g., automatic artwork image captioning for digital archive applications.

The increasing availability of time series datasets enabled by the diffusion of IoT architectures and the progress in the analysis of temporal data fostered by Deep Learning methods are boosting the interest in anomaly detection and predictive maintenance applications. The analysis of performance for these tasks relies on standard metrics applied to the entire dataset. Such indicators provide a global performance assessment but might not provide a deep understanding of the model weaknesses. A complementary diagnostic approach exploits error categorization and ad hoc visualizations. In this paper, we present ODIN TS, an open source diagnosis framework for time series analysis that lets developers compute performance metrics, disaggregated by different criteria, and visualize diagnosis reports. ODIN TS is agnostic to the training platform and can be extended with application- and domain-specific meta-annotations and metrics with almost no coding. We show ODIN TS at work through two time series analytics examples.

Iconography in art is the discipline that studies the visual content of artworks to determine their motifs and themes and to characterize the way these are represented. It is a subject of active research for a variety of purposes, including the interpretation of meaning, the investigation of the origin and diffusion in time and space of representations, and the study of influences across artists and artworks. With the proliferation of digital archives of art images, the possibility arises of applying Computer Vision techniques to the analysis of art images at an unprecedented scale, which may support iconography research and education. In this article, we introduce a novel paintings dataset for iconography classification and present the quantitative and qualitative results of applying a Convolutional Neural Network ( CNN ) classifier to the recognition of the iconography of artworks. The proposed classifier achieves good performances (71.17% Precision, 70.89% Recall, 70.25% F1-Score, and 72.73% Average Precision) in the task of identifying saints in Christian religious paintings, a task made difficult by the presence of classes with very similar visual features. Qualitative analysis of the results shows that the CNN focuses on the traditional iconic motifs that characterize the representation of each saint and exploits such hints to attain correct identification. The ultimate goal of our work is to enable the automatic extraction, decomposition, and comparison of iconography elements to support iconographic studies and automatic artwork annotation.

Iconography studies the visual content of artworks by considering the themes portrayed in them and their representation. Computer Vision has been used to identify iconographic subjects in paintings and Convolutional Neural Networks enabled the effective classification of characters in Christian art paintings. However, it still has to be demonstrated if the classification results obtained by CNNs rely on the same iconographic properties that human experts exploit when studying iconography and if the architecture of a classifier trained on whole artwork images can be exploited to support the much harder task of object detection. A suitable approach for exposing the process of classification by neural models relies on Class Activation Maps, which emphasize the areas of an image contributing the most to the classification. This work compares state-of-the-art algorithms (CAM, Grad-CAM, Grad-CAM++, and Smooth Grad-CAM++) in terms of their capacity of identifying the iconographic attributes that determine the classification of characters in Christian art paintings. Quantitative and qualitative analyses show that Grad-CAM, Grad-CAM++, and Smooth Grad-CAM++ have similar performances while CAM has lower efficacy. Smooth Grad-CAM++ isolates multiple disconnected image regions that identify small iconographic symbols well. Grad-CAM produces wider and more contiguous areas that cover large iconographic symbols better. The salient image areas computed by the CAM algorithms have been used to estimate object-level bounding boxes and a quantitative analysis shows that the boxes estimated with Grad-CAM reach 55% average IoU, 61% GT-known localization and 31% mAP. The obtained results are a step towards the computer-aided study of the variations of iconographic elements positioning and mutual relations in artworks and open the way to the automatic creation of bounding boxes for training detectors of iconographic symbols in Christian art images.

LOW-COST RUBBER COMPOUNDS FOR FIBER-REINFORCED ELASTOMERIC ISOLATORS: RECOVERED POWDERS AND WASTE OILS FROM RUBBER MANUFACTURING PROCESSES - 8th International Conference on Computational Methods in Structural Dynamics and Earthquake Engineering - 28-30 June 2021, Streamed from Athens, Greece