Raul Gomez, Ali Furkan Biten, Lluis Gomez, Jaume Gibert, Marçal Rusiñol, & Dimosthenis Karatzas. (2019). Selective Style Transfer for Text. In 15th International Conference on Document Analysis and Recognition (pp. 805–812).
Abstract: This paper explores the possibilities of image style transfer applied to text maintaining the original transcriptions. Results on different text domains (scene text, machine printed text and handwritten text) and cross-modal results demonstrate that this is feasible, and open different research lines. Furthermore, two architectures for selective style transfer, which means
transferring style to only desired image pixels, are proposed. Finally, scene text selective style transfer is evaluated as a data augmentation technique to expand scene text detection datasets, resulting in a boost of text detectors performance. Our implementation of the described models is publicly available.
Keywords: transfer; text style transfer; data augmentation; scene text detection
|
Raul Gomez, Lluis Gomez, Jaume Gibert, & Dimosthenis Karatzas. (2019). Self-Supervised Learning from Web Data for Multimodal Retrieval. In Multi-Modal Scene Understanding Book (pp. 279–306).
Abstract: Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal data. In this work we propose to exploit this free available data to learn a multimodal image and text embedding, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the proposed pipeline can learn from images with associated text without supervision and analyze the semantic structure of the learnt joint image and text embeddingspace. Weperformathoroughanalysisandperformancecomparisonoffivedifferentstateof the art text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text basedimageretrievaltask,andweclearlyoutperformstateoftheartintheMIRFlickrdatasetwhen training in the target data. Further, we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.
Keywords: self-supervised learning; webly supervised learning; text embeddings; multimodal retrieval; multimodal embedding
|
Xialei Liu, Joost Van de Weijer, & Andrew Bagdanov. (2019). Exploiting Unlabeled Data in CNNs by Self-Supervised Learning to Rank. TPAMI - IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(8), 1862–1878.
Abstract: For many applications the collection of labeled data is expensive laborious. Exploitation of unlabeled data during training is thus a long pursued objective of machine learning. Self-supervised learning addresses this by positing an auxiliary task (different, but related to the supervised task) for which data is abundantly available. In this paper, we show how ranking can be used as a proxy task for some regression problems. As another contribution, we propose an efficient backpropagation technique for Siamese networks which prevents the redundant computation introduced by the multi-branch network architecture. We apply our framework to two regression problems: Image Quality Assessment (IQA) and Crowd Counting. For both we show how to automatically generate ranked image sets from unlabeled data. Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results for both IQA and crowd counting. In addition, we show that measuring network uncertainty on the self-supervised proxy task is a good measure of informativeness of unlabeled data. This can be used to drive an algorithm for active learning and we show that this reduces labeling effort by up to 50 percent.
Keywords: Task analysis;Training;Image quality;Visualization;Uncertainty;Labeling;Neural networks;Learning from rankings;image quality assessment;crowd counting;active learning
|
Rafael E. Rivadeneira, Patricia Suarez, Angel Sappa, & Boris X. Vintimilla. (2019). Thermal Image SuperResolution Through Deep Convolutional Neural Network. In 16th International Conference on Images Analysis and Recognition (pp. 417–426).
Abstract: Due to the lack of thermal image datasets, a new dataset has been acquired for proposed a super-resolution approach using a Deep Convolution Neural Network schema. In order to achieve this image enhancement process, a new thermal images dataset is used. Different experiments have been carried out, firstly, the proposed architecture has been trained using only images of the visible spectrum, and later it has been trained with images of the thermal spectrum, the results showed that with the network trained with thermal images, better results are obtained in the process of enhancing the images, maintaining the image details and perspective. The thermal dataset is available at http://www.
cidis.espol.edu.ec/es/dataset.
|
Angel Morera, Angel Sanchez, Angel Sappa, & Jose F. Velez. (2019). Robust Detection of Outdoor Urban Advertising Panels in Static Images. In 18th International Conference on Practical Applications of Agents and Multi-Agent Systems (pp. 246–256).
Abstract: One interesting publicity application for Smart City environments is recognizing brand information contained in urban advertising panels. For such a purpose, a previous stage is to accurately detect and locate the position of these panels in images. This work presents an effective solution to this problem using a Single Shot Detector (SSD) based on a deep neural network architecture that minimizes the number of false detections under multiple variable conditions regarding the panels and the scene. Achieved experimental results using the Intersection over Union (IoU) accuracy metric make this proposal applicable in real complex urban images.
Keywords: Object detection; Urban ads panels; Deep learning; Single Shot Detector (SSD) architecture; Intersection over Union (IoU) metric; Augmented Reality
|
Armin Mehri, & Angel Sappa. (2019). Colorizing Near Infrared Images through a Cyclic Adversarial Approach of Unpaired Samples. In IEEE International Conference on Computer Vision and Pattern Recognition-Workshops.
Abstract: This paper presents a novel approach for colorizing near infrared (NIR) images. The approach is based on image-to-image translation using a Cycle-Consistent adversarial network for learning the color channels on unpaired dataset. This architecture is able to handle unpaired datasets. The approach uses as generators tailored networks that require less computation times, converge faster and generate high quality samples. The obtained results have been quantitatively—using standard evaluation metrics—and qualitatively evaluated showing considerable improvements with respect to the state of the art
|
Patricia Suarez, Angel Sappa, Boris X. Vintimilla, & Riad I. Hammoud. (2019). Image Vegetation Index through a Cycle Generative Adversarial Network. In IEEE International Conference on Computer Vision and Pattern Recognition-Workshops.
Abstract: This paper proposes a novel approach to estimate the Normalized Difference Vegetation Index (NDVI) just from an RGB image. The NDVI values are obtained by using images from the visible spectral band together with a synthetic near infrared image obtained by a cycled GAN. The cycled GAN network is able to obtain a NIR image from a given gray scale image. It is trained by using unpaired set of gray scale and NIR images by using a U-net architecture and a multiple loss function (gray scale images are obtained from the provided RGB images). Then, the NIR image estimated with the proposed cycle generative adversarial network is used to compute the NDVI index. Experimental results are provided showing the validity of the proposed approach. Additionally, comparisons with previous approaches are also provided.
|
Victoria Ruiz, Angel Sanchez, Jose F. Velez, & Bogdan Raducanu. (2019). Automatic Image-Based Waste Classification. In International Work-Conference on the Interplay Between Natural and Artificial Computation. From Bioinspired Systems and Biomedical Applications to Machine Learning (Vol. 11487, 422–431). LNCS.
Abstract: The management of solid waste in large urban environments has become a complex problem due to increasing amount of waste generated every day by citizens and companies. Current Computer Vision and Deep Learning techniques can help in the automatic detection and classification of waste types for further recycling tasks. In this work, we use the TrashNet dataset to train and compare different deep learning architectures for automatic classification of garbage types. In particular, several Convolutional Neural Networks (CNN) architectures were compared: VGG, Inception and ResNet. The best classification results were obtained using a combined Inception-ResNet model that achieved 88.6% of accuracy. These are the best results obtained with the considered dataset.
Keywords: Computer Vision; Deep learning; Convolutional neural networks; Waste classification
|
David Berga, Xose R. Fernandez-Vidal, Xavier Otazu, V. Leboran, & Xose M. Pardo. (2019). Psychophysical evaluation of individual low-level feature influences on visual attention. VR - Vision Research, 154, 60–79.
Abstract: In this study we provide the analysis of eye movement behavior elicited by low-level feature distinctiveness with a dataset of synthetically-generated image patterns. Design of visual stimuli was inspired by the ones used in previous psychophysical experiments, namely in free-viewing and visual searching tasks, to provide a total of 15 types of stimuli, divided according to the task and feature to be analyzed. Our interest is to analyze the influences of low-level feature contrast between a salient region and the rest of distractors, providing fixation localization characteristics and reaction time of landing inside the salient region. Eye-tracking data was collected from 34 participants during the viewing of a 230 images dataset. Results show that saliency is predominantly and distinctively influenced by: 1. feature type, 2. feature contrast, 3. temporality of fixations, 4. task difficulty and 5. center bias. This experimentation proposes a new psychophysical basis for saliency model evaluation using synthetic images.
Keywords: Visual attention; Psychophysics; Saliency; Task; Context; Contrast; Center bias; Low-level; Synthetic; Dataset
|
Arnau Baro, Pau Riba, Jorge Calvo-Zaragoza, & Alicia Fornes. (2019). From Optical Music Recognition to Handwritten Music Recognition: a Baseline. PRL - Pattern Recognition Letters, 123, 1–8.
Abstract: Optical Music Recognition (OMR) is the branch of document image analysis that aims to convert images of musical scores into a computer-readable format. Despite decades of research, the recognition of handwritten music scores, concretely the Western notation, is still an open problem, and the few existing works only focus on a specific stage of OMR. In this work, we propose a full Handwritten Music Recognition (HMR) system based on Convolutional Recurrent Neural Networks, data augmentation and transfer learning, that can serve as a baseline for the research community.
|
Arnau Baro, Jialuo Chen, Alicia Fornes, & Beata Megyesi. (2019). Towards a generic unsupervised method for transcription of encoded manuscripts. In 3rd International Conference on Digital Access to Textual Cultural Heritage (pp. 73–78).
Abstract: Historical ciphers, a special type of manuscripts, contain encrypted information, important for the interpretation of our history. The first step towards decipherment is to transcribe the images, either manually or by automatic image processing techniques. Despite the improvements in handwritten text recognition (HTR) thanks to deep learning methodologies, the need of labelled data to train is an important limitation. Given that ciphers often use symbol sets across various alphabets and unique symbols without any transcription scheme available, these supervised HTR techniques are not suitable to transcribe ciphers. In this paper we propose an un-supervised method for transcribing encrypted manuscripts based on clustering and label propagation, which has been successfully applied to community detection in networks. We analyze the performance on ciphers with various symbol sets, and discuss the advantages and drawbacks compared to supervised HTR methods.
Keywords: A. Baró, J. Chen, A. Fornés, B. Megyesi.
|
Lichao Zhang, Abel Gonzalez-Garcia, Joost Van de Weijer, Martin Danelljan, & Fahad Shahbaz Khan. (2019). Learning the Model Update for Siamese Trackers. In 18th IEEE International Conference on Computer Vision (pp. 4009–4018).
Abstract: Siamese approaches address the visual tracking problem by extracting an appearance template from the current frame, which is used to localize the target in the next frame. In general, this template is linearly combined with the accumulated template from the previous frame, resulting in an exponential decay of information over time. While such an approach to updating has led to improved results, its simplicity limits the potential gain likely to be obtained by learning to update. Therefore, we propose to replace the handcrafted update function with a method which learns to update. We use a convolutional neural network, called UpdateNet, which given the initial template, the accumulated template and the template of the current frame aims to estimate the optimal template for the next frame. The UpdateNet is compact and can easily be integrated into existing Siamese trackers. We demonstrate the generality of the proposed approach by applying it to two Siamese trackers, SiamFC and DaSiamRPN. Extensive experiments on VOT2016, VOT2018, LaSOT, and TrackingNet datasets demonstrate that our UpdateNet effectively predicts the new target template, outperforming the standard linear update. On the large-scale TrackingNet dataset, our UpdateNet improves the results of DaSiamRPN with an absolute gain of 3.9% in terms of success score.
|
Md.Mostafa Kamal Sarker, Hatem A. Rashwan, Farhan Akram, Estefania Talavera, Syeda Furruka Banu, Petia Radeva, et al. (2019). Recognizing Food Places in Egocentric Photo-Streams Using Multi-Scale Atrous Convolutional Networks and Self-Attention Mechanism. ACCESS - IEEE Access, 7, 39069–39082.
Abstract: Wearable sensors (e.g., lifelogging cameras) represent very useful tools to monitor people's daily habits and lifestyle. Wearable cameras are able to continuously capture different moments of the day of their wearers, their environment, and interactions with objects, people, and places reflecting their personal lifestyle. The food places where people eat, drink, and buy food, such as restaurants, bars, and supermarkets, can directly affect their daily dietary intake and behavior. Consequently, developing an automated monitoring system based on analyzing a person's food habits from daily recorded egocentric photo-streams of the food places can provide valuable means for people to improve their eating habits. This can be done by generating a detailed report of the time spent in specific food places by classifying the captured food place images to different groups. In this paper, we propose a self-attention mechanism with multi-scale atrous convolutional networks to generate discriminative features from image streams to recognize a predetermined set of food place categories. We apply our model on an egocentric food place dataset called “EgoFoodPlaces” that comprises of 43 392 images captured by 16 individuals using a lifelogging camera. The proposed model achieved an overall classification accuracy of 80% on the “EgoFoodPlaces” dataset, respectively, outperforming the baseline methods, such as VGG16, ResNet50, and InceptionV3.
|
Lichao Zhang, Martin Danelljan, Abel Gonzalez-Garcia, Joost Van de Weijer, & Fahad Shahbaz Khan. (2019). Multi-Modal Fusion for End-to-End RGB-T Tracking. In IEEE International Conference on Computer Vision Workshops (pp. 2252–2261).
Abstract: We propose an end-to-end tracking framework for fusing the RGB and TIR modalities in RGB-T tracking. Our baseline tracker is DiMP (Discriminative Model Prediction), which employs a carefully designed target prediction network trained end-to-end using a discriminative loss. We analyze the effectiveness of modality fusion in each of the main components in DiMP, i.e. feature extractor, target estimation network, and classifier. We consider several fusion mechanisms acting at different levels of the framework, including pixel-level, feature-level and response-level. Our tracker is trained in an end-to-end manner, enabling the components to learn how to fuse the information from both modalities. As data to train our model, we generate a large-scale RGB-T dataset by considering an annotated RGB tracking dataset (GOT-10k) and synthesizing paired TIR images using an image-to-image translation approach. We perform extensive experiments on VOT-RGBT2019 dataset and RGBT210 dataset, evaluating each type of modality fusing on each model component. The results show that the proposed fusion mechanisms improve the performance of the single modality counterparts. We obtain our best results when fusing at the feature-level on both the IoU-Net and the model predictor, obtaining an EAO score of 0.391 on VOT-RGBT2019 dataset. With this fusion mechanism we achieve the state-of-the-art performance on RGBT210 dataset.
|
Lu Yu, Vacit Oguz Yazici, Xialei Liu, Joost Van de Weijer, Yongmei Cheng, & Arnau Ramisa. (2019). Learning Metrics from Teachers: Compact Networks for Image Embedding. In 32nd IEEE Conference on Computer Vision and Pattern Recognition (pp. 2907–2916).
Abstract: Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image embeddings with small networks. Network distillation has been successfully applied to improve image classification, but has hardly been explored for metric learning. To do so, we propose two new loss functions that model the
communication of a deep teacher network to a small student network. We evaluate our system in several datasets, including CUB-200-2011, Cars-196, Stanford Online Products and show that embeddings computed using small student networks perform significantly better than those computed using standard networks of similar size. Results on a very compact network (MobileNet-0.25), which can be
used on mobile devices, show that the proposed method can greatly improve Recall@1 results from 27.5% to 44.6%. Furthermore, we investigate various aspects of distillation for embeddings, including hint and attention layers, semisupervised learning and cross quality distillation.
|
