Klara Janousckova, Jiri Matas, Lluis Gomez, & Dimosthenis Karatzas. (2020). Text Recognition – Real World Data and Where to Find Them. In 25th International Conference on Pattern Recognition (pp. 4489–4496).
Abstract: We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach uses an arbitrary end-to-end text recognition system to obtain text region proposals and their, possibly erroneous, transcriptions. The method includes matching of imprecise transcriptions to weak annotations and an edit distance guided neighbourhood search. It produces nearly error-free, localised instances of scene text, which we treat as “pseudo ground truth” (PGT). The method is applied to two weakly-annotated datasets. Training with the extracted PGT consistently improves the accuracy of a state of the art recognition model, by 3.7% on average, across different benchmark datasets (image domains) and 24.5% on one of the weakly annotated datasets 1 1 Acknowledgements. The authors were supported by Czech Technical University student grant SGS20/171/0HK3/3TJ13, the MEYS VVV project CZ.02.1.01/0.010.0J16 019/0000765 Research Center for Informatics, the Spanish Research project TIN2017-89779-P and the CERCA Programme / Generalitat de Catalunya.
|
Minesh Mathew, Ruben Tito, Dimosthenis Karatzas, R.Manmatha, & C.V. Jawahar. (2020). Document Visual Question Answering Challenge 2020. In 33rd IEEE Conference on Computer Vision and Pattern Recognition – Short paper.
Abstract: This paper presents results of Document Visual Question Answering Challenge organized as part of “Text and Documents in the Deep Learning Era” workshop, in CVPR 2020. The challenge introduces a new problem – Visual Question Answering on document images. The challenge comprised two tasks. The first task concerns with asking questions on a single document image. On the other hand, the second task is set as a retrieval task where the question is posed over a collection of images. For the task 1 a new dataset is introduced comprising 50,000 questions-answer(s) pairs defined over 12,767 document images. For task 2 another dataset has been created comprising 20 questions over 14,362 document images which share the same document template.
|
Carola Figueroa Flores, David Berga, Joost Van de Weijer, & Bogdan Raducanu. (2021). Saliency for free: Saliency prediction as a side-effect of object recognition. PRL - Pattern Recognition Letters, 150, 1–7.
Abstract: Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects instead of the background. So far, computational methods for saliency estimation required the explicit generation of a saliency map, process which is usually achieved via eyetracking experiments on still images. This is a tedious process that needs to be repeated for each new dataset. In the current paper, we demonstrate that is possible to automatically generate saliency maps without ground-truth. In our approach, saliency maps are learned as a side effect of object recognition. Extensive experiments carried out on both real and synthetic datasets demonstrated that our approach is able to generate accurate saliency maps, achieving competitive results when compared with supervised methods.
Keywords: Saliency maps; Unsupervised learning; Object recognition
|
Ozge Mercanoglu Sincan, Julio C. S. Jacques Junior, Sergio Escalera, & Hacer Yalim Keles. (2021). ChaLearn LAP Large Scale Signer Independent Isolated Sign Language Recognition Challenge: Design, Results and Future Research. In Conference on Computer Vision and Pattern Recognition Workshops (pp. 3467–3476).
Abstract: The performances of Sign Language Recognition (SLR) systems have improved considerably in recent years. However, several open challenges still need to be solved to allow SLR to be useful in practice. The research in the field is in its infancy in regards to the robustness of the models to a large diversity of signs and signers, and to fairness of the models to performers from different demographics. This work summarises the ChaLearn LAP Large Scale Signer Independent Isolated SLR Challenge, organised at CVPR 2021 with the goal of overcoming some of the aforementioned challenges. We analyse and discuss the challenge design, top winning solutions and suggestions for future research. The challenge attracted 132 participants in the RGB track and 59 in the RGB+Depth track, receiving more than 1.5K submissions in total. Participants were evaluated using a new large-scale multi-modal Turkish Sign Language (AUTSL) dataset, consisting of 226 sign labels and 36,302 isolated sign video samples performed by 43 different signers. Winning teams achieved more than 96% recognition rate, and their approaches benefited from pose/hand/face estimation, transfer learning, external data, fusion/ensemble of modalities and different strategies to model spatio-temporal information. However, methods still fail to distinguish among very similar signs, in particular those sharing similar hand trajectories.
|
Daniel Hernandez, Antonio Espinosa, David Vazquez, Antonio Lopez, & Juan C. Moure. (2021). 3D Perception With Slanted Stixels on GPU. TPDS - IEEE Transactions on Parallel and Distributed Systems, 32(10), 2434–2447.
Abstract: This article presents a GPU-accelerated software design of the recently proposed model of Slanted Stixels, which represents the geometric and semantic information of a scene in a compact and accurate way. We reformulate the measurement depth model to reduce the computational complexity of the algorithm, relying on the confidence of the depth estimation and the identification of invalid values to handle outliers. The proposed massively parallel scheme and data layout for the irregular computation pattern that corresponds to a Dynamic Programming paradigm is described and carefully analyzed in performance terms. Performance is shown to scale gracefully on current generation embedded GPUs. We assess the proposed methods in terms of semantic and geometric accuracy as well as run-time performance on three publicly available benchmark datasets. Our approach achieves real-time performance with high accuracy for 2048 × 1024 image sizes and 4 × 4 Stixel resolution on the low-power embedded GPU of an NVIDIA Tegra Xavier.
Keywords: Daniel Hernandez-Juarez; Antonio Espinosa; David Vazquez; Antonio M. Lopez; Juan C. Moure
|
Jose Luis Gomez, Gabriel Villalonga, & Antonio Lopez. (2021). Co-Training for Deep Object Detection: Comparing Single-Modal and Multi-Modal Approaches. SENS - Sensors, 21(9), 3185.
Abstract: Top-performing computer vision models are powered by convolutional neural networks (CNNs). Training an accurate CNN highly depends on both the raw sensor data and their associated ground truth (GT). Collecting such GT is usually done through human labeling, which is time-consuming and does not scale as we wish. This data-labeling bottleneck may be intensified due to domain shifts among image sensors, which could force per-sensor data labeling. In this paper, we focus on the use of co-training, a semi-supervised learning (SSL) method, for obtaining self-labeled object bounding boxes (BBs), i.e., the GT to train deep object detectors. In particular, we assess the goodness of multi-modal co-training by relying on two different views of an image, namely, appearance (RGB) and estimated depth (D). Moreover, we compare appearance-based single-modal co-training with multi-modal. Our results suggest that in a standard SSL setting (no domain shift, a few human-labeled data) and under virtual-to-real domain shift (many virtual-world labeled data, no human-labeled data) multi-modal co-training outperforms single-modal. In the latter case, by performing GAN-based domain translation both co-training modalities are on par, at least when using an off-the-shelf depth estimation model not specifically trained on the translated images.
Keywords: co-training; multi-modality; vision-based object detection; ADAS; self-driving
|
Shiqi Yang, Kai Wang, Luis Herranz, & Joost Van de Weijer. (2021). On Implicit Attribute Localization for Generalized Zero-Shot Learning. IEEE Signal Processing Letters, 28, 872–876.
Abstract: Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions. Since attributes are often related to specific parts of objects, many recent works focus on discovering discriminative regions. However, these methods usually require additional complex part detection modules or attention mechanisms. In this paper, 1) we show that common ZSL backbones (without explicit attention nor part detection) can implicitly localize attributes, yet this property is not exploited. 2) Exploiting it, we then propose SELAR, a simple method that further encourages attribute localization, surprisingly achieving very competitive generalized ZSL (GZSL) performance when compared with more complex state-of-the-art methods. Our findings provide useful insight for designing future GZSL methods, and SELAR provides an easy to implement yet strong baseline.
|
Domicele Jonauskaite, Lucia Camenzind, C. Alejandro Parraga, Cecile N Diouf, Mathieu Mercapide Ducommun, Lauriane Müller, et al. (2021). Colour-emotion associations in individuals with red-green colour blindness. PeerJ, 9, e11180.
Abstract: Colours and emotions are associated in languages and traditions. Some of us may convey sadness by saying feeling blue or by wearing black clothes at funerals. The first example is a conceptual experience of colour and the second example is an immediate perceptual experience of colour. To investigate whether one or the other type of experience more strongly drives colour-emotion associations, we tested 64 congenitally red-green colour-blind men and 66 non-colour-blind men. All participants associated 12 colours, presented as terms or patches, with 20 emotion concepts, and rated intensities of the associated emotions. We found that colour-blind and non-colour-blind men associated similar emotions with colours, irrespective of whether colours were conveyed via terms (r = .82) or patches (r = .80). The colour-emotion associations and the emotion intensities were not modulated by participants' severity of colour blindness. Hinting at some additional, although minor, role of actual colour perception, the consistencies in associations for colour terms and patches were higher in non-colour-blind than colour-blind men. Together, these results suggest that colour-emotion associations in adults do not require immediate perceptual colour experiences, as conceptual experiences are sufficient.
Keywords: Affect; Chromotherapy; Colour cognition; Colour vision deficiency; Cross-modal correspondences; Daltonism; Deuteranopia; Dichromatic; Emotion; Protanopia.
|
Marc Masana, Tinne Tuytelaars, & Joost Van de Weijer. (2021). Ternary Feature Masks: zero-forgetting for task-incremental learning. In 34th IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 3565–3574).
Abstract: We propose an approach without any forgetting to continual learning for the task-aware regime, where at inference the task-label is known. By using ternary masks we can upgrade a model to new tasks, reusing knowledge from previous tasks while not forgetting anything about them. Using masks prevents both catastrophic forgetting and backward transfer. We argue -- and show experimentally -- that avoiding the former largely compensates for the lack of the latter, which is rarely observed in practice. In contrast to earlier works, our masks are applied to the features (activations) of each layer instead of the weights. This considerably reduces the number of mask parameters for each new task; with more than three orders of magnitude for most networks. The encoding of the ternary masks into two bits per feature creates very little overhead to the network, avoiding scalability issues. To allow already learned features to adapt to the current task without changing the behavior of these features for previous tasks, we introduce task-specific feature normalization. Extensive experiments on several finegrained datasets and ImageNet show that our method outperforms current state-of-the-art while reducing memory overhead in comparison to weight-based approaches.
|
Kai Wang, Luis Herranz, & Joost Van de Weijer. (2021). Continual learning in cross-modal retrieval. In 2nd CLVISION workshop (pp. 3628–3638).
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.
|
Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu, Antonio Carta, Gabriele Graffieti, Tyler L. Hayes, et al. (2021). Avalanche: an End-to-End Library for Continual Learning. In 34th IEEE Conference on Computer Vision and Pattern Recognition Workshops (pp. 3595–3605).
Abstract: Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.
|
Sudeep Katakol, Luis Herranz, Fei Yang, & Marta Mrak. (2021). DANICE: Domain adaptation without forgetting in neural image compression. In Conference on Computer Vision and Pattern Recognition Workshops (pp. 1921–1925).
Abstract: Neural image compression (NIC) is a new coding paradigm where coding capabilities are captured by deep models learned from data. This data-driven nature enables new potential functionalities. In this paper, we study the adaptability of codecs to custom domains of interest. We show that NIC codecs are transferable and that they can be adapted with relatively few target domain images. However, naive adaptation interferes with the solution optimized for the original source domain, resulting in forgetting the original coding capabilities in that domain, and may even break the compatibility with previously encoded bitstreams. Addressing these problems, we propose Codec Adaptation without Forgetting (CAwF), a framework that can avoid these problems by adding a small amount of custom parameters, where the source codec remains embedded and unchanged during the adaptation process. Experiments demonstrate its effectiveness and provide useful insights on the characteristics of catastrophic interference in NIC.
|
Fei Yang, Luis Herranz, Yongmei Cheng, & Mikhail Mozerov. (2021). Slimmable compressive autoencoders for practical neural image compression. In 34th IEEE Conference on Computer Vision and Pattern Recognition (pp. 4996–5005).
Abstract: Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single rate, limiting their practical use. Focusing on practical image compression, we propose slimmable compressive autoencoders (SlimCAEs), where rate (R) and distortion (D) are jointly optimized for different capacities. Once trained, encoders and decoders can be executed at different capacities, leading to different rates and complexities. We show that a successful implementation of SlimCAEs requires suitable capacity-specific RD tradeoffs. Our experiments show that SlimCAEs are highly flexible models that provide excellent rate-distortion performance, variable rate, and dynamic adjustment of memory, computational cost and latency, thus addressing the main requirements of practical image compression.
|
Arturo Fuentes, F. Javier Sanchez, Thomas Voncina, & Jorge Bernal. (2021). LAMV: Learning to Predict Where Spectators Look in Live Music Performances. In 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Vol. 5, pp. 500–507).
Abstract: The advent of artificial intelligence has supposed an evolution on how different daily work tasks are performed. The analysis of cultural content has seen a huge boost by the development of computer-assisted methods that allows easy and transparent data access. In our case, we deal with the automation of the production of live shows, like music concerts, aiming to develop a system that can indicate the producer which camera to show based on what each of them is showing. In this context, we consider that is essential to understand where spectators look and what they are interested in so the computational method can learn from this information. The work that we present here shows the results of a first preliminary study in which we compare areas of interest defined by human beings and those indicated by an automatic system. Our system is based on the extraction of motion textures from dynamic Spatio-Temporal Volumes (STV) and then analyzing the patterns by means of texture analysis techniques. We validate our approach over several video sequences that have been labeled by 16 different experts. Our method is able to match those relevant areas identified by the experts, achieving recall scores higher than 80% when a distance of 80 pixels between method and ground truth is considered. Current performance shows promise when detecting abnormal peaks and movement trends.
|
Adria Molina, Pau Riba, Lluis Gomez, Oriol Ramos Terrades, & Josep Llados. (2021). Date Estimation in the Wild of Scanned Historical Photos: An Image Retrieval Approach. In 16th International Conference on Document Analysis and Recognition (Vol. 12822, pp. 306–320). LNCS.
Abstract: This paper presents a novel method for date estimation of historical photographs from archival sources. The main contribution is to formulate the date estimation as a retrieval task, where given a query, the retrieved images are ranked in terms of the estimated date similarity. The closer are their embedded representations the closer are their dates. Contrary to the traditional models that design a neural network that learns a classifier or a regressor, we propose a learning objective based on the nDCG ranking metric. We have experimentally evaluated the performance of the method in two different tasks: date estimation and date-sensitive image retrieval, using the DEW public database, overcoming the baseline methods.
|
