Albin Soutif, Marc Masana, Joost Van de Weijer, & Bartlomiej Twardowski. (2021). On the importance of cross-task features for class-incremental learning. In Theory and Foundation of continual learning workshop of ICML.
Abstract: In class-incremental learning, an agent with limited resources needs to learn a sequence of classification tasks, forming an ever growing classification problem, with the constraint of not being able to access data from previous tasks. The main difference with task-incremental learning, where a task-ID is available at inference time, is that the learner also needs to perform crosstask discrimination, i.e. distinguish between classes that have not been seen together. Approaches to tackle this problem are numerous and mostly make use of an external memory (buffer) of non-negligible size. In this paper, we ablate the learning of crosstask features and study its influence on the performance of basic replay strategies used for class-IL. We also define a new forgetting measure for class-incremental learning, and see that forgetting is not the principal cause of low performance. Our experimental results show that future algorithms for class-incremental learning should not only prevent forgetting, but also aim to improve the quality of the cross-task features. This is especially important when the number of classes per task is small.
|
Diego Velazquez, Josep M. Gonfaus, Pau Rodriguez, Xavier Roca, Seiichi Ozawa, & Jordi Gonzalez. (2021). Logo Detection With No Priors. ACCESS - IEEE Access, 9, 106998–107011.
Abstract: In recent years, top referred methods on object detection like R-CNN have implemented this task as a combination of proposal region generation and supervised classification on the proposed bounding boxes. Although this pipeline has achieved state-of-the-art results in multiple datasets, it has inherent limitations that make object detection a very complex and inefficient task in computational terms. Instead of considering this standard strategy, in this paper we enhance Detection Transformers (DETR) which tackles object detection as a set-prediction problem directly in an end-to-end fully differentiable pipeline without requiring priors. In particular, we incorporate Feature Pyramids (FP) to the DETR architecture and demonstrate the effectiveness of the resulting DETR-FP approach on improving logo detection results thanks to the improved detection of small logos. So, without requiring any domain specific prior to be fed to the model, DETR-FP obtains competitive results on the OpenLogo and MS-COCO datasets offering a relative improvement of up to 30%, when compared to a Faster R-CNN baseline which strongly depends on hand-designed priors.
|
Trevor Canham, Javier Vazquez, Elise Mathieu, & Marcelo Bertalmío. (2021). Matching visual induction effects on screens of different size. JOV - Journal of Vision, 21(6(10)), 1–22.
Abstract: In the film industry, the same movie is expected to be watched on displays of vastly different sizes, from cinema screens to mobile phones. But visual induction, the perceptual phenomenon by which the appearance of a scene region is affected by its surroundings, will be different for the same image shown on two displays of different dimensions. This phenomenon presents a practical challenge for the preservation of the artistic intentions of filmmakers, because it can lead to shifts in image appearance between viewing destinations. In this work, we show that a neural field model based on the efficient representation principle is able to predict induction effects and how, by regularizing its associated energy functional, the model is still able to represent induction but is now invertible. From this finding, we propose a method to preprocess an image in a screen–size dependent way so that its perception, in terms of visual induction, may remain constant across displays of different size. The potential of the method is demonstrated through psychophysical experiments on synthetic images and qualitative examples on natural images.
|
Meysam Madadi, Hugo Bertiche, & Sergio Escalera. (2021). Deep unsupervised 3D human body reconstruction from a sparse set of landmarks. IJCV - International Journal of Computer Vision, 129, 2499–2512.
Abstract: In this paper we propose the first deep unsupervised approach in human body reconstruction to estimate body surface from a sparse set of landmarks, so called DeepMurf. We apply a denoising autoencoder to estimate missing landmarks. Then we apply an attention model to estimate body joints from landmarks. Finally, a cascading network is applied to regress parameters of a statistical generative model that reconstructs body. Our set of proposed loss functions allows us to train the network in an unsupervised way. Results on four public datasets show that our approach accurately reconstructs the human body from real world mocap data.
|
Pau Riba, Adria Molina, Lluis Gomez, Oriol Ramos Terrades, & Josep Llados. (2021). Learning to Rank Words: Optimizing Ranking Metrics for Word Spotting. In 16th International Conference on Document Analysis and Recognition (Vol. 12822, 381–395).
Abstract: In this paper, we explore and evaluate the use of ranking-based objective functions for learning simultaneously a word string and a word image encoder. We consider retrieval frameworks in which the user expects a retrieval list ranked according to a defined relevance score. In the context of a word spotting problem, the relevance score has been set according to the string edit distance from the query string. We experimentally demonstrate the competitive performance of the proposed model on query-by-string word spotting for both, handwritten and real scene word images. We also provide the results for query-by-example word spotting, although it is not the main focus of this work.
|
Alejandro Cartas, Petia Radeva, & Mariella Dimiccoli. (2021). Modeling long-term interactions to enhance action recognition. In 25th International Conference on Pattern Recognition (pp. 10351–10358).
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
|
Ruben Tito, Minesh Mathew, C.V. Jawahar, Ernest Valveny, & Dimosthenis Karatzas. (2021). ICDAR 2021 Competition on Document Visual Question Answering. In 16th International Conference on Document Analysis and Recognition (pp. 635–649).
Abstract: In this report we present results of the ICDAR 2021 edition of the Document Visual Question Challenges. This edition complements the previous tasks on Single Document VQA and Document Collection VQA with a newly introduced on Infographics VQA. Infographics VQA is based on a new dataset of more than 5, 000 infographics images and 30, 000 question-answer pairs. The winner methods have scored 0.6120 ANLS in Infographics VQA task, 0.7743 ANLSL in Document Collection VQA task and 0.8705 ANLS in Single Document VQA. We present a summary of the datasets used for each task, description of each of the submitted methods and the results and analysis of their performance. A summary of the progress made on Single Document VQA since the first edition of the DocVQA 2020 challenge is also presented.
|
Hassan Ahmed Sial. (2021). Estimating Light Effects from a Single Image: Deep Architectures and Ground-Truth Generation (Maria Vanrell, & Ramon Baldrich, Eds.). Ph.D. thesis, IMPRIMA, .
Abstract: In this thesis, we explore how to estimate the effects of the light interacting with the scene objects from a single image. To achieve this goal, we focus on recovering intrinsic components like reflectance, shading, or light properties such as color and position using deep architectures. The success of these approaches relies on training on large and diversified image datasets. Therefore, we present several contributions on this such as: (a) a data-augmentation technique; (b) a ground-truth for an existing multi-illuminant dataset; (c) a family of synthetic datasets, SID for Surreal Intrinsic Datasets, with diversified backgrounds and coherent light conditions; and (d) a practical pipeline to create hybrid ground-truths to overcome the complexity of acquiring realistic light conditions in a massive way. In parallel with the creation of datasets, we trained different flexible encoder-decoder deep architectures incorporating physical constraints from the image formation models.
In the last part of the thesis, we apply all the previous experience to two different problems. Firstly, we create a large hybrid Doc3DShade dataset with real shading and synthetic reflectance under complex illumination conditions, that is used to train a two-stage architecture that improves the character recognition task in complex lighting conditions of unwrapped documents. Secondly, we tackle the problem of single image scene relighting by extending both, the SID dataset to present stronger shading and shadows effects, and the deep architectures to use intrinsic components to estimate new relit images.
|
Andres Mafla, Ruben Tito, Sounak Dey, Lluis Gomez, Marçal Rusiñol, Ernest Valveny, et al. (2021). Real-time Lexicon-free Scene Text Retrieval. PR - Pattern Recognition, 110, 107656.
Abstract: In this work, we address the task of scene text retrieval: given a text query, the system returns all images containing the queried text. The proposed model uses a single shot CNN architecture that predicts bounding boxes and builds a compact representation of spotted words. In this way, this problem can be modeled as a nearest neighbor search of the textual representation of a query over the outputs of the CNN collected from the totality of an image database. Our experiments demonstrate that the proposed model outperforms previous state-of-the-art, while offering a significant increase in processing speed and unmatched expressiveness with samples never seen at training time. Several experiments to assess the generalization capability of the model are conducted in a multilingual dataset, as well as an application of real-time text spotting in videos.
|
Yasuko Sugito, Trevor Canham, Javier Vazquez, & Marcelo Bertalmio. (2021). A Study of Objective Quality Metrics for HLG-Based HDR/WCG Image Coding. SMPTE - SMPTE Motion Imaging Journal, 53–65.
Abstract: In this work, we study the suitability of high dynamic range, wide color gamut (HDR/WCG) objective quality metrics to assess the perceived deterioration of compressed images encoded using the hybrid log-gamma (HLG) method, which is the standard for HDR television. Several image quality metrics have been developed to deal specifically with HDR content, although in previous work we showed that the best results (i.e., better matches to the opinion of human expert observers) are obtained by an HDR metric that consists simply in applying a given standard dynamic range metric, called visual information fidelity (VIF), directly to HLG-encoded images. However, all these HDR metrics ignore the chroma components for their calculations, that is, they consider only the luminance channel. For this reason, in the current work, we conduct subjective evaluation experiments in a professional setting using compressed HDR/WCG images encoded with HLG and analyze the ability of the best HDR metric to detect perceivable distortions in the chroma components, as well as the suitability of popular color metrics (including ΔITPR , which supports parameters for HLG) to correlate with the opinion scores. Our first contribution is to show that there is a need to consider the chroma components in HDR metrics, as there are color distortions that subjects perceive but that the best HDR metric fails to detect. Our second contribution is the surprising result that VIF, which utilizes only the luminance channel, correlates much better with the subjective evaluation scores than the metrics investigated that do consider the color components.
|
Sanket Biswas, Pau Riba, Josep Llados, & Umapada Pal. (2021). Beyond Document Object Detection: Instance-Level Segmentation of Complex Layouts. IJDAR - International Journal on Document Analysis and Recognition, 24, 269–281.
Abstract: Information extraction is a fundamental task of many business intelligence services that entail massive document processing. Understanding a document page structure in terms of its layout provides contextual support which is helpful in the semantic interpretation of the document terms. In this paper, inspired by the progress of deep learning methodologies applied to the task of object recognition, we transfer these models to the specific case of document object detection, reformulating the traditional problem of document layout analysis. Moreover, we importantly contribute to prior arts by defining the task of instance segmentation on the document image domain. An instance segmentation paradigm is especially important in complex layouts whose contents should interact for the proper rendering of the page, i.e., the proper text wrapping around an image. Finally, we provide an extensive evaluation, both qualitative and quantitative, that demonstrates the superior performance of the proposed methodology over the current state of the art.
|
Yaxing Wang, Abel Gonzalez-Garcia, Luis Herranz, & Joost Van de Weijer. (2021). Controlling biases and diversity in diverse image-to-image translation. CVIU - Computer Vision and Image Understanding, 202, 103082.
Abstract: JCR 2019 Q2, IF=3.121
The task of unpaired image-to-image translation is highly challenging due to the lack of explicit cross-domain pairs of instances. We consider here diverse image translation (DIT), an even more challenging setting in which an image can have multiple plausible translations. This is normally achieved by explicitly disentangling content and style in the latent representation and sampling different styles codes while maintaining the image content. Despite the success of current DIT models, they are prone to suffer from bias. In this paper, we study the problem of bias in image-to-image translation. Biased datasets may add undesired changes (e.g. change gender or race in face images) to the output translations as a consequence of the particular underlying visual distribution in the target domain. In order to alleviate the effects of this problem we propose the use of semantic constraints that enforce the preservation of desired image properties. Our proposed model is a step towards unbiased diverse image-to-image translation (UDIT), and results in less unwanted changes in the translated images while still performing the wanted transformation. Experiments on several heavily biased datasets show the effectiveness of the proposed techniques in different domains such as faces, objects, and scenes.
|
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.
|
Armin Mehri, Parichehr Behjati Ardakani, & Angel Sappa. (2021). MPRNet: Multi-Path Residual Network for Lightweight Image Super Resolution. In IEEE Winter Conference on Applications of Computer Vision (pp. 2703–2712).
Abstract: Lightweight super resolution networks have extremely importance for real-world applications. In recent years several SR deep learning approaches with outstanding achievement have been introduced by sacrificing memory and computational cost. To overcome this problem, a novel lightweight super resolution network is proposed, which improves the SOTA performance in lightweight SR and performs roughly similar to computationally expensive networks. Multi-Path Residual Network designs with a set of Residual concatenation Blocks stacked with Adaptive Residual Blocks: ($i$) to adaptively extract informative features and learn more expressive spatial context information; ($ii$) to better leverage multi-level representations before up-sampling stage; and ($iii$) to allow an efficient information and gradient flow within the network. The proposed architecture also contains a new attention mechanism, Two-Fold Attention Module, to maximize the representation ability of the model. Extensive experiments show the superiority of our model against other SOTA SR approaches.
|
Gabriel Villalonga. (2021). Leveraging Synthetic Data to Create Autonomous Driving Perception Systems (Antonio Lopez, & German Ros, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Manually annotating images to develop vision models has been a major bottleneck
since computer vision and machine learning started to walk together. This has
been more evident since computer vision falls on the shoulders of data-hungry
deep learning techniques. When addressing on-board perception for autonomous
driving, the curse of data annotation is exacerbated due to the use of additional
sensors such as LiDAR. Therefore, any approach aiming at reducing such a timeconsuming and costly work is of high interest for addressing autonomous driving
and, in fact, for any application requiring some sort of artificial perception. In the
last decade, it has been shown that leveraging from synthetic data is a paradigm
worth to pursue in order to minimizing manual data annotation. The reason is
that the automatic process of generating synthetic data can also produce different
types of associated annotations (e.g. object bounding boxes for synthetic images
and LiDAR pointclouds, pixel/point-wise semantic information, etc.). Directly
using synthetic data for training deep perception models may not be the definitive
solution in all circumstances since it can appear a synth-to-real domain shift. In
this context, this work focuses on leveraging synthetic data to alleviate manual
annotation for three perception tasks related to driving assistance and autonomous
driving. In all cases, we assume the use of deep convolutional neural networks
(CNNs) to develop our perception models.
The first task addresses traffic sign recognition (TSR), a kind of multi-class
classification problem. We assume that the number of sign classes to be recognized
must be suddenly increased without having annotated samples to perform the
corresponding TSR CNN re-training. We show that leveraging synthetic samples of
such new classes and transforming them by a generative adversarial network (GAN)
trained on the known classes (i.e. without using samples from the new classes), it is
possible to re-train the TSR CNN to properly classify all the signs for a ∼ 1/4 ratio of
new/known sign classes. The second task addresses on-board 2D object detection,
focusing on vehicles and pedestrians. In this case, we assume that we receive a set
of images without the annotations required to train an object detector, i.e. without
object bounding boxes. Therefore, our goal is to self-annotate these images so
that they can later be used to train the desired object detector. In order to reach
this goal, we leverage from synthetic data and propose a semi-supervised learning
approach based on the co-training idea. In fact, we use a GAN to reduce the synthto-real domain shift before applying co-training. Our quantitative results show
that co-training and GAN-based image-to-image translation complement each
other up to allow the training of object detectors without manual annotation, and still almost reaching the upper-bound performances of the detectors trained from
human annotations. While in previous tasks we focus on vision-based perception,
the third task we address focuses on LiDAR pointclouds. Our initial goal was to
develop a 3D object detector trained on synthetic LiDAR-style pointclouds. While
for images we may expect synth/real-to-real domain shift due to differences in
their appearance (e.g. when source and target images come from different camera
sensors), we did not expect so for LiDAR pointclouds since these active sensors
factor out appearance and provide sampled shapes. However, in practice, we have
seen that it can be domain shift even among real-world LiDAR pointclouds. Factors
such as the sampling parameters of the LiDARs, the sensor suite configuration onboard the ego-vehicle, and the human annotation of 3D bounding boxes, do induce
a domain shift. We show it through comprehensive experiments with different
publicly available datasets and 3D detectors. This redirected our goal towards the
design of a GAN for pointcloud-to-pointcloud translation, a relatively unexplored
topic.
Finally, it is worth to mention that all the synthetic datasets used for these three
tasks, have been designed and generated in the context of this PhD work and will
be publicly released. Overall, we think this PhD presents several steps forward to
encourage leveraging synthetic data for developing deep perception models in the
field of driving assistance and autonomous driving.
|