Abstract: Document classification is an important task in all the processes related to document storage and retrieval. In the case of complex documents, structural features are needed to achieve a correct classification. Unfortunately, physical layout analysis is error prone. In this paper we present a pre-segmentation step based on a divide & conquer strategy that can be used to improve the page segmentation results, independently of the segmentation algorithm used. This pre-segmentation step is evaluated in classification and retrieval using the selective CRLA algorithm for layout segmentation together with a clustering based on the voronoi area diagram, and tested on two different databases, MARG and Girona Archives.

Abstract: This paper presents a new method for human detection based on a multiresolution cascade of Histograms of Oriented Gradients (HOG) that can highly reduce the computational cost of the detection search without affecting accuracy. The method consists of a cascade of sliding window detectors. Each detector is a Support Vector Machine (SVM) composed by features at different resolution, from coarse for the first level to fine for the last one.
Considering that the spatial stride of the sliding window search is affected by the HOG features size, unlike previous methods based on Adaboost cascades, we can adopt a spatial stride inversely proportional to the features resolution. This produces that the speed-up of the cascade is not only due to the low number of features that need to be computed in the first levels, but also to the lower number of detection windows that needs to be evaluated.
Experimental results shows that our method permits a detection rate comparable with the state of the art, but at the same time a gain in the speed of the detection search of 10-20 times depending on the cascade configuration.

Abstract: In the last years, the interest in Optical Music Recognition (OMR) has reawakened, especially since the appearance of deep learning. However, there are very few works addressing handwritten scores. In this work we describe a full OMR pipeline for handwritten music scores by using Convolutional and Recurrent Neural Networks that could serve as a baseline for the research community.

Abstract: Online continual learning aims to get closer to a live learning experience by learning directly on a stream of data with temporally shifting distribution and by storing a minimum amount of data from that stream. In this empirical evaluation, we evaluate various methods from the literature that tackle online continual learning. More specifically, we focus on the class-incremental setting in the context of image classification, where the learner must learn new classes incrementally from a stream of data. We compare these methods on the Split-CIFAR100 and Split-TinyImagenet benchmarks, and measure their average accuracy, forgetting, stability, and quality of the representations, to evaluate various aspects of the algorithm at the end but also during the whole training period. We find that most methods suffer from stability and underfitting issues. However, the learned representations are comparable to i.i.d. training under the same computational budget. No clear winner emerges from the results and basic experience replay, when properly tuned and implemented, is a very strong baseline. We release our modular and extensible codebase at this https URL based on the avalanche framework to reproduce our results and encourage future research.

Abstract: Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While different methods have been explored to achieve this goal, we still lack understanding of the resulting reduction patterns and how those patterns differ across token reduction methods and datasets. To close this gap, we set out to understand the reduction patterns of 10 different token reduction methods using four image classification datasets. By systematically comparing these methods on the different classification tasks, we find that the Top-K pruning method is a surprisingly strong baseline. Through in-depth analysis of the different methods, we determine that: the reduction patterns are generally not consistent when varying the capacity of the backbone model, the reduction patterns of pruning-based methods significantly differ from fixed radial patterns, and the reduction patterns of pruning-based methods are correlated across classification datasets. Finally we report that the similarity of reduction patterns is a moderate-to-strong proxy for model performance. Project page at https://vap.aau.dk/tokens.

Abstract: Test-time adaptation is a promising research direction that allows the source model to adapt itself to changes in data distribution without any supervision. Yet, current methods are usually evaluated on benchmarks that are only a simplification of real-world scenarios. Hence, we propose to validate test-time adaptation methods using the recently introduced datasets for autonomous driving, namely CLAD-C and SHIFT. We observe that current test-time adaptation methods struggle to effectively handle varying degrees of domain shift, often resulting in degraded performance that falls below that of the source model. We noticed that the root of the problem lies in the inability to preserve the knowledge of the source model and adapt to dynamically changing, temporally correlated data streams. Therefore, we enhance well-established self-training framework by incorporating a small memory buffer to increase model stability and at the same time perform dynamic adaptation based on the intensity of domain shift. The proposed method, named AR-TTA, outperforms existing approaches on both synthetic and more real-world benchmarks and shows robustness across a variety of TTA scenarios.