| Home | << 1 2 3 4 5 6 7 8 9 >> |
|
| Records | |||||
|---|---|---|---|---|---|
| Author | Lu Yu; Bartlomiej Twardowski; Xialei Liu; Luis Herranz; Kai Wang; Yongmai Cheng; Shangling Jui; Joost Van de Weijer | ||||
Title  |
Semantic Drift Compensation for Class-Incremental Learning of Embeddings | Type | Conference Article | ||
| Year | 2020 | Publication | 33rd IEEE Conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this setting, networks suffer from catastrophic forgetting which refers to the drastic drop in performance on previous tasks. The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes. Embedding networks have the advantage that new classes can be naturally included into the network without adding new weights. Therefore, we study incremental learning for embedding networks. In addition, we propose a new method to estimate the drift, called semantic drift, of features and compensate for it without the need of any exemplars. We approximate the drift of previous tasks based on the drift that is experienced by current task data. We perform experiments on fine-grained datasets, CIFAR100 and ImageNet-Subset. We demonstrate that embedding networks suffer significantly less from catastrophic forgetting. We outperform existing methods which do not require exemplars and obtain competitive results compared to methods which store exemplars. Furthermore, we show that our proposed SDC when combined with existing methods to prevent forgetting consistently improves results. | ||||
| Address | Virtual CVPR | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | CVPR | ||
| Notes | LAMP; 600.141; 601.309; 602.200; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ YTL2020 | Serial | 3422 | ||
| Permanent link to this record | |||||
| Author | Aymen Azaza; Joost Van de Weijer; Ali Douik; Javad Zolfaghari Bengar; Marc Masana | ||||
| Title |
Saliency from High-Level Semantic Image Features | Type | Journal | ||
| Year | 2020 | Publication | SN Computer Science | Abbreviated Journal | SN |
| Volume | 1 | Issue | 4 | Pages | 1-12 |
| Keywords | |||||
| Abstract | Top-down semantic information is known to play an important role in assigning saliency. Recently, large strides have been made in improving state-of-the-art semantic image understanding in the fields of object detection and semantic segmentation. Therefore, since these methods have now reached a high-level of maturity, evaluation of the impact of high-level image understanding on saliency estimation is now feasible. We propose several saliency features which are computed from object detection and semantic segmentation results. We combine these features with a standard baseline method for saliency detection to evaluate their importance. Experiments demonstrate that the proposed features derived from object detection and semantic segmentation improve saliency estimation significantly. Moreover, they show that our method obtains state-of-the-art results on (FT, ImgSal, and SOD datasets) and obtains competitive results on four other datasets (ECSSD, PASCAL-S, MSRA-B, and HKU-IS). | ||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | LAMP; 600.120; 600.109; 600.106 | Approved | no | ||
| Call Number | Admin @ si @ AWD2020 | Serial | 3503 | ||
| Permanent link to this record | |||||
| Author | Lei Kang | ||||
| Title |
Robust Handwritten Text Recognition in Scarce Labeling Scenarios: Disentanglement, Adaptation and Generation | Type | Book Whole | ||
| Year | 2020 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Handwritten documents are not only preserved in historical archives but also widely used in administrative documents such as cheques and claims. With the rise of the deep learning era, many state-of-the-art approaches have achieved good performance on specific datasets for Handwritten Text Recognition (HTR). However, it is still challenging to solve real use cases because of the varied handwriting styles across different writers and the limited labeled data. Thus, both explorin a more robust handwriting recognition architectures and proposing methods to diminish the gap between the source and target data in an unsupervised way are
demanded. In this thesis, firstly, we explore novel architectures for HTR, from Sequence-to-Sequence (Seq2Seq) method with attention mechanism to non-recurrent Transformer-based method. Secondly, we focus on diminishing the performance gap between source and target data in an unsupervised way. Finally, we propose a group of generative methods for handwritten text images, which could be utilized to increase the training set to obtain a more robust recognizer. In addition, by simply modifying the generative method and joining it with a recognizer, we end up with an effective disentanglement method to distill textual content from handwriting styles so as to achieve a generalized recognition performance. We outperform state-of-the-art HTR performances in the experimental results among different scientific and industrial datasets, which prove the effectiveness of the proposed methods. To the best of our knowledge, the non-recurrent recognizer and the disentanglement method are the first contributions in the handwriting recognition field. Furthermore, we have outlined the potential research lines, which would be interesting to explore in the future. |
||||
| Address | |||||
| Corporate Author | Thesis | Ph.D. thesis | |||
| Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Alicia Fornes;Marçal Rusiñol;Mauricio Villegas | |
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | 978-84-122714-0-9 | Medium | ||
| Area | Expedition | Conference | |||
| Notes | DAG; 600.121 | Approved | no | ||
| Call Number | Admin @ si @ Kan20 | Serial | 3482 | ||
| Permanent link to this record | |||||
| Author | Sangeeth Reddy; Minesh Mathew; Lluis Gomez; Marçal Rusiñol; Dimosthenis Karatzas; C.V. Jawahar | ||||
| Title |
RoadText-1K: Text Detection and Recognition Dataset for Driving Videos | Type | Conference Article | ||
| Year | 2020 | Publication | IEEE International Conference on Robotics and Automation | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Perceiving text is crucial to understand semantics of outdoor scenes and hence is a critical requirement to build intelligent systems for driver assistance and self-driving. Most of the existing datasets for text detection and recognition comprise still images and are mostly compiled keeping text in mind. This paper introduces a new ”RoadText-1K” dataset for text in driving videos. The dataset is 20 times larger than the existing largest dataset for text in videos. Our dataset comprises 1000 video clips of driving without any bias towards text and with annotations for text bounding boxes and transcriptions in every frame. State of the art methods for text detection,
recognition and tracking are evaluated on the new dataset and the results signify the challenges in unconstrained driving videos compared to existing datasets. This suggests that RoadText-1K is suited for research and development of reading systems, robust enough to be incorporated into more complex downstream tasks like driver assistance and self-driving. The dataset can be found at http://cvit.iiit.ac.in/research/ projects/cvit-projects/roadtext-1k |
||||
| Address | Paris; Francia; ??? | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | ICRA | ||
| Notes | DAG; 600.121; 600.129 | Approved | no | ||
| Call Number | Admin @ si @ RMG2020 | Serial | 3400 | ||
| Permanent link to this record | |||||
| Author | Cristina Sanchez Montes; Jorge Bernal; Ana Garcia Rodriguez; Henry Cordova; Gloria Fernandez Esparrach | ||||
| Title |
Revisión de métodos computacionales de detección y clasificación de pólipos en imagen de colonoscopia | Type | Journal Article | ||
| Year | 2020 | Publication | Gastroenterología y Hepatología | Abbreviated Journal | GH |
| Volume | 43 | Issue | 4 | Pages | 222-232 |
| Keywords | |||||
| Abstract | Computer-aided diagnosis (CAD) is a tool with great potential to help endoscopists in the tasks of detecting and histologically classifying colorectal polyps. In recent years, different technologies have been described and their potential utility has been increasingly evidenced, which has generated great expectations among scientific societies. However, most of these works are retrospective and use images of different quality and characteristics which are analysed off line. This review aims to familiarise gastroenterologists with computational methods and the particularities of endoscopic imaging, which have an impact on image processing analysis. Finally, the publicly available image databases, needed to compare and confirm the results obtained with different methods, are presented. | ||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | MV; | Approved | no | ||
| Call Number | Admin @ si @ SBG2020 | Serial | 3404 | ||
| Permanent link to this record | |||||
| Author | Raul Gomez; Yahui Liu; Marco de Nadai; Dimosthenis Karatzas; Bruno Lepri; Nicu Sebe | ||||
| Title |
Retrieval Guided Unsupervised Multi-domain Image to Image Translation | Type | Conference Article | ||
| Year | 2020 | Publication | 28th ACM International Conference on Multimedia | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Image to image translation aims to learn a mapping that transforms an image from one visual domain to another. Recent works assume that images descriptors can be disentangled into a domain-invariant content representation and a domain-specific style representation. Thus, translation models seek to preserve the content of source images while changing the style to a target visual domain. However, synthesizing new images is extremely challenging especially in multi-domain translations, as the network has to compose content and style to generate reliable and diverse images in multiple domains. In this paper we propose the use of an image retrieval system to assist the image-to-image translation task. First, we train an image-to-image translation model to map images to multiple domains. Then, we train an image retrieval model using real and generated images to find images similar to a query one in content but in a different domain. Finally, we exploit the image retrieval system to fine-tune the image-to-image translation model and generate higher quality images. Our experiments show the effectiveness of the proposed solution and highlight the contribution of the retrieval network, which can benefit from additional unlabeled data and help image-to-image translation models in the presence of scarce data. | ||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | ACM | ||
| Notes | DAG; 600.121 | Approved | no | ||
| Call Number | Admin @ si @ GLN2020 | Serial | 3497 | ||
| Permanent link to this record | |||||
| Author | Riccardo Del Chiaro; Bartlomiej Twardowski; Andrew Bagdanov; Joost Van de Weijer | ||||
| Title |
Recurrent attention to transient tasks for continual image captioning | Type | Conference Article | ||
| Year | 2020 | Publication | 34th Conference on Neural Information Processing Systems | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Research on continual learning has led to a variety of approaches to mitigating catastrophic forgetting in feed-forward classification networks. Until now surprisingly little attention has been focused on continual learning of recurrent models applied to problems like image captioning. In this paper we take a systematic look at continual learning of LSTM-based models for image captioning. We propose an attention-based approach that explicitly accommodates the transient nature of vocabularies in continual image captioning tasks -- i.e. that task vocabularies are not disjoint. We call our method Recurrent Attention to Transient Tasks (RATT), and also show how to adapt continual learning approaches based on weight egularization and knowledge distillation to recurrent continual learning problems. We apply our approaches to incremental image captioning problem on two new continual learning benchmarks we define using the MS-COCO and Flickr30 datasets. Our results demonstrate that RATT is able to sequentially learn five captioning tasks while incurring no forgetting of previously learned ones. | ||||
| Address | virtual; December 2020 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | NEURIPS | ||
| Notes | LAMP; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ CTB2020 | Serial | 3484 | ||
| Permanent link to this record | |||||
| Author | Gabriel Villalonga; Joost Van de Weijer; Antonio Lopez | ||||
| Title |
Recognizing new classes with synthetic data in the loop: application to traffic sign recognition | Type | Journal Article | ||
| Year | 2020 | Publication | Sensors | Abbreviated Journal | SENS |
| Volume | 20 | Issue | 3 | Pages | 583 |
| Keywords | |||||
| Abstract | On-board vision systems may need to increase the number of classes that can be recognized in a relatively short period. For instance, a traffic sign recognition system may suddenly be required to recognize new signs. Since collecting and annotating samples of such new classes may need more time than we wish, especially for uncommon signs, we propose a method to generate these samples by combining synthetic images and Generative Adversarial Network (GAN) technology. In particular, the GAN is trained on synthetic and real-world samples from known classes to perform synthetic-to-real domain adaptation, but applied to synthetic samples of the new classes. Using the Tsinghua dataset with a synthetic counterpart, SYNTHIA-TS, we have run an extensive set of experiments. The results show that the proposed method is indeed effective, provided that we use a proper Convolutional Neural Network (CNN) to perform the traffic sign recognition (classification) task as well as a proper GAN to transform the synthetic images. Here, a ResNet101-based classifier and domain adaptation based on CycleGAN performed extremely well for a ratio∼ 1/4 for new/known classes; even for more challenging ratios such as∼ 4/1, the results are also very positive. | ||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | LAMP; ADAS; 600.118; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ VWL2020 | Serial | 3405 | ||
| Permanent link to this record | |||||
| Author | Idoia Ruiz; Joan Serrat | ||||
| Title |
Rank-based ordinal classification | Type | Conference Article | ||
| Year | 2020 | Publication | 25th International Conference on Pattern Recognition | Abbreviated Journal | |
| Volume | Issue | Pages | 8069-8076 | ||
| Keywords | |||||
| Abstract | Differently from the regular classification task, in ordinal classification there is an order in the classes. As a consequence not all classification errors matter the same: a predicted class close to the groundtruth one is better than predicting a farther away class. To account for this, most previous works employ loss functions based on the absolute difference between the predicted and groundtruth class labels. We argue that there are many cases in ordinal classification where label values are arbitrary (for instance 1. . . C, being C the number of classes) and thus such loss functions may not be the best choice. We instead propose a network architecture that produces not a single class prediction but an ordered vector, or ranking, of all the possible classes from most to least likely. This is thanks to a loss function that compares groundtruth and predicted rankings of these class labels, not the labels themselves. Another advantage of this new formulation is that we can enforce consistency in the predictions, namely, predicted rankings come from some unimodal vector of scores with mode at the groundtruth class. We compare with the state of the art ordinal classification methods, showing
that ours attains equal or better performance, as measured by common ordinal classification metrics, on three benchmark datasets. Furthermore, it is also suitable for a new task on image aesthetics assessment, i.e. most voted score prediction. Finally, we also apply it to building damage assessment from satellite images, providing an analysis of its performance depending on the degree of imbalance of the dataset. |
||||
| Address | Virtual; January 2021 | ||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | ICPR | ||
| Notes | ADAS; 600.118; 600.124 | Approved | no | ||
| Call Number | Admin @ si @ RuS2020 | Serial | 3549 | ||
| Permanent link to this record | |||||
| Author | Giovanni Maria Farinella; Petia Radeva; Jose Braz | ||||
| Title |
Proceedings of the 15th International Joint Conference on Computer Vision; Imaging and Computer Graphics Theory and Applications | Type | Book Whole | ||
| Year | 2020 | Publication | Proceedings of the 15th International Joint Conference on Computer Vision; Imaging and Computer Graphics Theory and Applications; VISIGRAPP 2020 | Abbreviated Journal | |
| Volume | 4 | Issue | Pages | ||
| Keywords | |||||
| Abstract | |||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | MILAB | Approved | no | ||
| Call Number | Admin @ si @ FRB2020a | Serial | 3546 | ||
| Permanent link to this record | |||||
| Author | Giovanni Maria Farinella; Petia Radeva; Jose Braz | ||||
| Title |
Proceedings of the 15th International Joint Conference on Computer Vision; Imaging and Computer Graphics Theory and Applications | Type | Book Whole | ||
| Year | 2020 | Publication | Proceedings of the 15th International Joint Conference on Computer Vision; Imaging and Computer Graphics Theory and Applications; VISIGRAPP 2020 | Abbreviated Journal | |
| Volume | 5 | Issue | Pages | ||
| Keywords | |||||
| Abstract | |||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | MILAB | Approved | no | ||
| Call Number | Admin @ si @ FRB2020b | Serial | 3547 | ||
| Permanent link to this record | |||||
| Author | Ana Garcia Rodriguez; Jorge Bernal; F. Javier Sanchez; Henry Cordova; Rodrigo Garces Duran; Cristina Rodriguez de Miguel; Gloria Fernandez Esparrach | ||||
| Title |
Polyp fingerprint: automatic recognition of colorectal polyps’ unique features | Type | Journal Article | ||
| Year | 2020 | Publication | Surgical Endoscopy and other Interventional Techniques | Abbreviated Journal | SEND |
| Volume | 34 | Issue | 4 | Pages | 1887-1889 |
| Keywords | |||||
| Abstract | BACKGROUND:
Content-based image retrieval (CBIR) is an application of machine learning used to retrieve images by similarity on the basis of features. Our objective was to develop a CBIR system that could identify images containing the same polyp ('polyp fingerprint'). METHODS: A machine learning technique called Bag of Words was used to describe each endoscopic image containing a polyp in a unique way. The system was tested with 243 white light images belonging to 99 different polyps (for each polyp there were at least two images representing it in two different temporal moments). Images were acquired in routine colonoscopies at Hospital Clínic using high-definition Olympus endoscopes. The method provided for each image the closest match within the dataset. RESULTS: The system matched another image of the same polyp in 221/243 cases (91%). No differences were observed in the number of correct matches according to Paris classification (protruded: 90.7% vs. non-protruded: 91.3%) and size (< 10 mm: 91.6% vs. > 10 mm: 90%). CONCLUSIONS: A CBIR system can match accurately two images containing the same polyp, which could be a helpful aid for polyp image recognition. KEYWORDS: Artificial intelligence; Colorectal polyps; Content-based image retrieval |
||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | MV; no menciona | Approved | no | ||
| Call Number | Admin @ si @ | Serial | 3403 | ||
| Permanent link to this record | |||||
| Author | Pau Rodriguez; Diego Velazquez; Guillem Cucurull; Josep M. Gonfaus; Xavier Roca; Seiichi Ozawa; Jordi Gonzalez | ||||
| Title |
Personality Trait Analysis in Social Networks Based on Weakly Supervised Learning of Shared Images | Type | Journal Article | ||
| Year | 2020 | Publication | Applied Sciences | Abbreviated Journal | APPLSCI |
| Volume | 10 | Issue | 22 | Pages | 8170 |
| Keywords | sentiment analysis, personality trait analysis; weakly-supervised learning; visual classification; OCEAN model; social networks | ||||
| Abstract | Social networks have attracted the attention of psychologists, as the behavior of users can be used to assess personality traits, and to detect sentiments and critical mental situations such as depression or suicidal tendencies. Recently, the increasing amount of image uploads to social networks has shifted the focus from text to image-based personality assessment. However, obtaining the ground-truth requires giving personality questionnaires to the users, making the process very costly and slow, and hindering research on large populations. In this paper, we demonstrate that it is possible to predict which images are most associated with each personality trait of the OCEAN personality model, without requiring ground-truth personality labels. Namely, we present a weakly supervised framework which shows that the personality scores obtained using specific images textually associated with particular personality traits are highly correlated with scores obtained using standard text-based personality questionnaires. We trained an OCEAN trait model based on Convolutional Neural Networks (CNNs), learned from 120K pictures posted with specific textual hashtags, to infer whether the personality scores from the images uploaded by users are consistent with those scores obtained from text. In order to validate our claims, we performed a personality test on a heterogeneous group of 280 human subjects, showing that our model successfully predicts which kind of image will match a person with a given level of a trait. Looking at the results, we obtained evidence that personality is not only correlated with text, but with image content too. Interestingly, different visual patterns emerged from those images most liked by persons with a particular personality trait: for instance, pictures most associated with high conscientiousness usually contained healthy food, while low conscientiousness pictures contained injuries, guns, and alcohol. These findings could pave the way to complement text-based personality questionnaires with image-based questions. | ||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | ISE; 600.119 | Approved | no | ||
| Call Number | Admin @ si @ RVC2020b | Serial | 3553 | ||
| Permanent link to this record | |||||
| Author | Pau Rodriguez; Diego Velazquez; Guillem Cucurull; Josep M. Gonfaus; Xavier Roca; Jordi Gonzalez | ||||
| Title |
Pay attention to the activations: a modular attention mechanism for fine-grained image recognition | Type | Journal Article | ||
| Year | 2020 | Publication | IEEE Transactions on Multimedia | Abbreviated Journal | TMM |
| Volume | 22 | Issue | 2 | Pages | 502-514 |
| Keywords | |||||
| Abstract | Fine-grained image recognition is central to many multimedia tasks such as search, retrieval, and captioning. Unfortunately, these tasks are still challenging since the appearance of samples of the same class can be more different than those from different classes. This issue is mainly due to changes in deformation, pose, and the presence of clutter. In the literature, attention has been one of the most successful strategies to handle the aforementioned problems. Attention has been typically implemented in neural networks by selecting the most informative regions of the image that improve classification. In contrast, in this paper, attention is not applied at the image level but to the convolutional feature activations. In essence, with our approach, the neural model learns to attend to lower-level feature activations without requiring part annotations and uses those activations to update and rectify the output likelihood distribution. The proposed mechanism is modular, architecture-independent, and efficient in terms of both parameters and computation required. Experiments demonstrate that well-known networks such as wide residual networks and ResNeXt, when augmented with our approach, systematically improve their classification accuracy and become more robust to changes in deformation and pose and to the presence of clutter. As a result, our proposal reaches state-of-the-art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford Dogs, and UEC-Food100 while obtaining competitive performance in ImageNet, CIFAR-100, CUB200 Birds, and Stanford Cars. In addition, we analyze the different components of our model, showing that the proposed attention modules succeed in finding the most discriminative regions of the image. Finally, as a proof of concept, we demonstrate that with only local predictions, an augmented neural network can successfully classify an image before reaching any fully connected layer, thus reducing the computational amount up to 10%. | ||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | |||
| Notes | ISE; 600.119; 600.098 | Approved | no | ||
| Call Number | Admin @ si @ RVC2020a | Serial | 3417 | ||
| Permanent link to this record | |||||
| Author | Vacit Oguz Yazici; Abel Gonzalez-Garcia; Arnau Ramisa; Bartlomiej Twardowski; Joost Van de Weijer | ||||
| Title |
Orderless Recurrent Models for Multi-label Classification | Type | Conference Article | ||
| Year | 2020 | Publication | 33rd IEEE Conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Recurrent neural networks (RNN) are popular for many computer vision tasks, including multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered for the multi-label classification task. Current approaches sort labels according to their frequency, typically ordering them in either rare-first or frequent-first. These imposed orderings do not take into account that the natural order to generate the labels can change for each image, e.g.\ first the dominant object before summing up the smaller objects in the image. Therefore, in this paper, we propose ways to dynamically order the ground truth labels with the predicted label sequence. This allows for the faster training of more optimal LSTM models for multi-label classification. Analysis evidences that our method does not suffer from duplicate generation, something which is common for other models. Furthermore, it outperforms other CNN-RNN models, and we show that a standard architecture of an image encoder and language decoder trained with our proposed loss obtains the state-of-the-art results on the challenging MS-COCO, WIDER Attribute and PA-100K and competitive results on NUS-WIDE. | ||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Place of Publication | Editor | |||
| Language | Summary Language | Original Title | |||
| Series Editor | Series Title | Abbreviated Series Title | |||
| Series Volume | Series Issue | Edition | |||
| ISSN | ISBN | Medium | |||
| Area | Expedition | Conference | CVPR | ||
| Notes | LAMP; 600.109; 601.309; 600.141; 600.120 | Approved | no | ||
| Call Number | Admin @ si @ YGR2020 | Serial | 3408 | ||
| Permanent link to this record | |||||