| Records |
| Author |
Akhil Gurram; Antonio Lopez |
| Title |
On the Metrics for Evaluating Monocular Depth Estimation |
Type |
Miscellaneous |
| Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
|
| Keywords |
|
| Abstract |
Monocular Depth Estimation (MDE) is performed to produce 3D information that can be used in downstream tasks such as those related to on-board perception for Autonomous Vehicles (AVs) or driver assistance. Therefore, a relevant arising question is whether the standard metrics for MDE assessment are a good indicator of the accuracy of future MDE-based driving-related perception tasks. We address this question in this paper. In particular, we take the task of 3D object detection on point clouds as a proxy of on-board perception. We train and test state-of-the-art 3D object detectors using 3D point clouds coming from MDE models. We confront the ranking of object detection results with the ranking given by the depth estimation metrics of the MDE models. We conclude that, indeed, MDE evaluation metrics give rise to a ranking of methods that reflects relatively well the 3D object detection results we may expect. Among the different metrics, the absolute relative (abs-rel) error seems to be the best for that purpose. |
| 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 |
ADAS |
Approved |
no |
| Call Number |
Admin @ si @ GuL2023 |
Serial  |
3867 |
| Permanent link to this record |
| |
|
| |
| Author |
Maciej Wielgosz; Antonio Lopez; Muhamad Naveed Riaz |
| Title |
CARLA-BSP: a simulated dataset with pedestrians |
Type |
Miscellaneous |
| Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
|
| Keywords |
|
| Abstract |
We present a sample dataset featuring pedestrians generated using the ARCANE framework, a new framework for generating datasets in CARLA (0.9.13). We provide use cases for pedestrian detection, autoencoding, pose estimation, and pose lifting. We also showcase baseline results. |
| 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 |
ADAS |
Approved |
no |
| Call Number |
Admin @ si @ WLN2023 |
Serial |
3866 |
| Permanent link to this record |
| |
|
| |
| Author |
Wenwen Fu; Zhihong An; Wendong Huang; Haoran Sun; Wenjuan Gong; Jordi Gonzalez |
| Title |
A Spatio-Temporal Spotting Network with Sliding Windows for Micro-Expression Detection |
Type |
Journal Article |
| Year |
2023 |
Publication |
Electronics |
Abbreviated Journal |
ELEC |
| Volume |
12 |
Issue |
18 |
Pages |
3947 |
| Keywords |
micro-expression spotting; sliding window; key frame extraction |
| Abstract |
Micro-expressions reveal underlying emotions and are widely applied in political psychology, lie detection, law enforcement and medical care. Micro-expression spotting aims to detect the temporal locations of facial expressions from video sequences and is a crucial task in micro-expression recognition. In this study, the problem of micro-expression spotting is formulated as micro-expression classification per frame. We propose an effective spotting model with sliding windows called the spatio-temporal spotting network. The method involves a sliding window detection mechanism, combines the spatial features from the local key frames and the global temporal features and performs micro-expression spotting. The experiments are conducted on the CAS(ME)2 database and the SAMM Long Videos database, and the results demonstrate that the proposed method outperforms the state-of-the-art method by 30.58% for the CAS(ME)2 and 23.98% for the SAMM Long Videos according to overall F-scores. |
| 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 |
Approved |
no |
| Call Number |
Admin @ si @ FAH2023 |
Serial |
3864 |
| Permanent link to this record |
| |
|
| |
| Author |
Bonifaz Stuhr; Jurgen Brauer; Bernhard Schick; Jordi Gonzalez |
| Title |
Masked Discriminators for Content-Consistent Unpaired Image-to-Image Translation |
Type |
Miscellaneous |
| Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
|
| Keywords |
|
| Abstract |
A common goal of unpaired image-to-image translation is to preserve content consistency between source images and translated images while mimicking the style of the target domain. Due to biases between the datasets of both domains, many methods suffer from inconsistencies caused by the translation process. Most approaches introduced to mitigate these inconsistencies do not constrain the discriminator, leading to an even more ill-posed training setup. Moreover, none of these approaches is designed for larger crop sizes. In this work, we show that masking the inputs of a global discriminator for both domains with a content-based mask is sufficient to reduce content inconsistencies significantly. However, this strategy leads to artifacts that can be traced back to the masking process. To reduce these artifacts, we introduce a local discriminator that operates on pairs of small crops selected with a similarity sampling strategy. Furthermore, we apply this sampling strategy to sample global input crops from the source and target dataset. In addition, we propose feature-attentive denormalization to selectively incorporate content-based statistics into the generator stream. In our experiments, we show that our method achieves state-of-the-art performance in photorealistic sim-to-real translation and weather translation and also performs well in day-to-night translation. Additionally, we propose the cKVD metric, which builds on the sKVD metric and enables the examination of translation quality at the class or category level. |
| 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 |
Approved |
no |
| Call Number |
Admin @ si @ SBS2023 |
Serial |
3863 |
| Permanent link to this record |
| |
|
| |
| Author |
Wenjuan Gong; Yue Zhang; Wei Wang; Peng Cheng; Jordi Gonzalez |
| Title |
Meta-MMFNet: Meta-learning-based Multi-model Fusion Network for Micro-expression Recognition |
Type |
Journal Article |
| Year |
2023 |
Publication |
ACM Transactions on Multimedia Computing, Communications, and Applications |
Abbreviated Journal |
TMCCA |
| Volume |
20 |
Issue |
2 |
Pages |
1–20 |
| Keywords |
|
| Abstract |
Despite its wide applications in criminal investigations and clinical communications with patients suffering from autism, automatic micro-expression recognition remains a challenging problem because of the lack of training data and imbalanced classes problems. In this study, we proposed a meta-learning-based multi-model fusion network (Meta-MMFNet) to solve the existing problems. The proposed method is based on the metric-based meta-learning pipeline, which is specifically designed for few-shot learning and is suitable for model-level fusion. The frame difference and optical flow features were fused, deep features were extracted from the fused feature, and finally in the meta-learning-based framework, weighted sum model fusion method was applied for micro-expression classification. Meta-MMFNet achieved better results than state-of-the-art methods on four datasets. The code is available at https://github.com/wenjgong/meta-fusion-based-method. |
| 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 |
Approved |
no |
| Call Number |
Admin @ si @ GZW2023 |
Serial |
3862 |
| Permanent link to this record |
| |
|
| |
| Author |
Parichehr Behjati; Pau Rodriguez; Carles Fernandez; Isabelle Hupont; Armin Mehri; Jordi Gonzalez |
| Title |
Single image super-resolution based on directional variance attention network |
Type |
Journal Article |
| Year |
2023 |
Publication |
Pattern Recognition |
Abbreviated Journal |
PR |
| Volume |
133 |
Issue |
|
Pages |
108997 |
| Keywords |
|
| Abstract |
Recent advances in single image super-resolution (SISR) explore the power of deep convolutional neural networks (CNNs) to achieve better performance. However, most of the progress has been made by scaling CNN architectures, which usually raise computational demands and memory consumption. This makes modern architectures less applicable in practice. In addition, most CNN-based SR methods do not fully utilize the informative hierarchical features that are helpful for final image recovery. In order to address these issues, we propose a directional variance attention network (DiVANet), a computationally efficient yet accurate network for SISR. Specifically, we introduce a novel directional variance attention (DiVA) mechanism to capture long-range spatial dependencies and exploit inter-channel dependencies simultaneously for more discriminative representations. Furthermore, we propose a residual attention feature group (RAFG) for parallelizing attention and residual block computation. The output of each residual block is linearly fused at the RAFG output to provide access to the whole feature hierarchy. In parallel, DiVA extracts most relevant features from the network for improving the final output and preventing information loss along the successive operations inside the network. Experimental results demonstrate the superiority of DiVANet over the state of the art in several datasets, while maintaining relatively low computation and memory footprint. The code is available at https://github.com/pbehjatii/DiVANet. |
| 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 |
Approved |
no |
| Call Number |
Admin @ si @ BPF2023 |
Serial |
3861 |
| Permanent link to this record |
| |
|
| |
| Author |
Khanh Nguyen; Ali Furkan Biten; Andres Mafla; Lluis Gomez; Dimosthenis Karatzas |
| Title |
Show, Interpret and Tell: Entity-Aware Contextualised Image Captioning in Wikipedia |
Type |
Conference Article |
| Year |
2023 |
Publication |
Proceedings of the 37th AAAI Conference on Artificial Intelligence |
Abbreviated Journal |
|
| Volume |
37 |
Issue |
2 |
Pages |
1940-1948 |
| Keywords |
|
| Abstract |
Humans exploit prior knowledge to describe images, and are able to adapt their explanation to specific contextual information given, even to the extent of inventing plausible explanations when contextual information and images do not match. In this work, we propose the novel task of captioning Wikipedia images by integrating contextual knowledge. Specifically, we produce models that jointly reason over Wikipedia articles, Wikimedia images and their associated descriptions to produce contextualized captions. The same Wikimedia image can be used to illustrate different articles, and the produced caption needs to be adapted to the specific context allowing us to explore the limits of the model to adjust captions to different contextual information. Dealing with out-of-dictionary words and Named Entities is a challenging task in this domain. To address this, we propose a pre-training objective, Masked Named Entity Modeling (MNEM), and show that this pretext task results to significantly improved models. Furthermore, we verify that a model pre-trained in Wikipedia generalizes well to News Captioning datasets. We further define two different test splits according to the difficulty of the captioning task. We offer insights on the role and the importance of each modality and highlight the limitations of our model. |
| Address |
Washington; USA; February 2023 |
| 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 |
AAAI |
| Notes |
DAG |
Approved |
no |
| Call Number |
Admin @ si @ NBM2023 |
Serial |
3860 |
| Permanent link to this record |
| |
|
| |
| Author |
Francesc Net; Marc Folia; Pep Casals; Lluis Gomez |
| Title |
Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections |
Type |
Conference Article |
| Year |
2023 |
Publication |
17th International Conference on Document Analysis and Recognition |
Abbreviated Journal |
|
| Volume |
14191 |
Issue |
|
Pages |
3-17 |
| Keywords |
Image deduplication; Near-duplicate images detection; Transductive Learning; Photographic Archives; Deep Learning |
| Abstract |
This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting duplicate and near-duplicate photographs can reduce the time spent on manual annotation by archivists. This real use case differs from laboratory settings as the deployment dataset is available in advance, allowing the use of transductive learning. We propose a transductive learning approach that leverages state-of-the-art deep learning architectures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). Our approach involves pre-training a deep neural network on a large dataset and then fine-tuning the network on the unlabeled target collection with self-supervised learning. The results show that the proposed approach outperforms the baseline methods in the task of near-duplicate image detection in the UKBench and an in-house private dataset. |
| Address |
San Jose; CA; USA; August 2023 |
| Corporate Author |
|
Thesis |
|
| Publisher |
|
Place of Publication |
|
Editor |
|
| Language |
|
Summary Language |
|
Original Title |
|
| Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
| Series Volume |
|
Series Issue |
|
Edition |
|
| ISSN |
|
ISBN |
|
Medium |
|
| Area |
|
Expedition |
|
Conference |
ICDAR |
| Notes |
DAG |
Approved |
no |
| Call Number |
Admin @ si @ NFC2023 |
Serial |
3859 |
| Permanent link to this record |
| |
|
| |
| Author |
M. Altillawi; S. Li; S.M. Prakhya; Z. Liu; Joan Serrat |
| Title |
Implicit Learning of Scene Geometry From Poses for Global Localization |
Type |
Journal Article |
| Year |
2024 |
Publication |
IEEE Robotics and Automation Letters |
Abbreviated Journal |
ROBOTAUTOMLET |
| Volume |
9 |
Issue |
2 |
Pages |
955-962 |
| Keywords |
Localization; Localization and mapping; Deep learning for visual perception; Visual learning |
| Abstract |
Global visual localization estimates the absolute pose of a camera using a single image, in a previously mapped area. Obtaining the pose from a single image enables many robotics and augmented/virtual reality applications. Inspired by latest advances in deep learning, many existing approaches directly learn and regress 6 DoF pose from an input image. However, these methods do not fully utilize the underlying scene geometry for pose regression. The challenge in monocular relocalization is the minimal availability of supervised training data, which is just the corresponding 6 DoF poses of the images. In this letter, we propose to utilize these minimal available labels (i.e., poses) to learn the underlying 3D geometry of the scene and use the geometry to estimate the 6 DoF camera pose. We present a learning method that uses these pose labels and rigid alignment to learn two 3D geometric representations ( X, Y, Z coordinates ) of the scene, one in camera coordinate frame and the other in global coordinate frame. Given a single image, it estimates these two 3D scene representations, which are then aligned to estimate a pose that matches the pose label. This formulation allows for the active inclusion of additional learning constraints to minimize 3D alignment errors between the two 3D scene representations, and 2D re-projection errors between the 3D global scene representation and 2D image pixels, resulting in improved localization accuracy. During inference, our model estimates the 3D scene geometry in camera and global frames and aligns them rigidly to obtain pose in real-time. We evaluate our work on three common visual localization datasets, conduct ablation studies, and show that our method exceeds state-of-the-art regression methods' pose accuracy on all datasets. |
| 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 |
2377-3766 |
ISBN |
|
Medium |
|
| Area |
|
Expedition |
|
Conference |
|
| Notes |
ADAS |
Approved |
no |
| Call Number |
Admin @ si @ |
Serial |
3857 |
| Permanent link to this record |
| |
|
| |
| Author |
Jose Elias Yauri; M. Lagos; H. Vega-Huerta; P. de-la-Cruz; G.L.E Maquen-Niño; E. Condor-Tinoco |
| Title |
Detection of Epileptic Seizures Based-on Channel Fusion and Transformer Network in EEG Recordings |
Type |
Journal Article |
| Year |
2023 |
Publication |
International Journal of Advanced Computer Science and Applications |
Abbreviated Journal |
IJACSA |
| Volume |
14 |
Issue |
5 |
Pages |
1067-1074 |
| Keywords |
Epilepsy; epilepsy detection; EEG; EEG channel fusion; convolutional neural network; self-attention |
| Abstract |
According to the World Health Organization, epilepsy affects more than 50 million people in the world, and specifically, 80% of them live in developing countries. Therefore, epilepsy has become among the major public issue for many governments and deserves to be engaged. Epilepsy is characterized by uncontrollable seizures in the subject due to a sudden abnormal functionality of the brain. Recurrence of epilepsy attacks change people’s lives and interferes with their daily activities. Although epilepsy has no cure, it could be mitigated with an appropriated diagnosis and medication. Usually, epilepsy diagnosis is based on the analysis of an electroencephalogram (EEG) of the patient. However, the process of searching for seizure patterns in a multichannel EEG recording is a visual demanding and time consuming task, even for experienced neurologists. Despite the recent progress in automatic recognition of epilepsy, the multichannel nature of EEG recordings still challenges current methods. In this work, a new method to detect epilepsy in multichannel EEG recordings is proposed. First, the method uses convolutions to perform channel fusion, and next, a self-attention network extracts temporal features to classify between interictal and ictal epilepsy states. The method was validated in the public CHB-MIT dataset using the k-fold cross-validation and achieved 99.74% of specificity and 99.15% of sensitivity, surpassing current approaches. |
| 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 |
IAM |
Approved |
no |
| Call Number |
Admin @ si @ |
Serial |
3856 |
| Permanent link to this record |
| |
|
| |
| Author |
Pau Cano; Alvaro Caravaca; Debora Gil; Eva Musulen |
| Title |
Diagnosis of Helicobacter pylori using AutoEncoders for the Detection of Anomalous Staining Patterns in Immunohistochemistry Images |
Type |
Miscellaneous |
| Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
107241 |
| Keywords |
|
| Abstract |
This work addresses the detection of Helicobacter pylori a bacterium classified since 1994 as class 1 carcinogen to humans. By its highest specificity and sensitivity, the preferred diagnosis technique is the analysis of histological images with immunohistochemical staining, a process in which certain stained antibodies bind to antigens of the biological element of interest. This analysis is a time demanding task, which is currently done by an expert pathologist that visually inspects the digitized samples.
We propose to use autoencoders to learn latent patterns of healthy tissue and detect H. pylori as an anomaly in image staining. Unlike existing classification approaches, an autoencoder is able to learn patterns in an unsupervised manner (without the need of image annotations) with high performance. In particular, our model has an overall 91% of accuracy with 86\% sensitivity, 96% specificity and 0.97 AUC in the detection of H. pylori. |
| 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 |
IAM |
Approved |
no |
| Call Number |
Admin @ si @ CCG2023 |
Serial |
3855 |
| Permanent link to this record |
| |
|
| |
| Author |
JW Xiao; CB Zhang; J. Feng; Xialei Liu; Joost Van de Weijer; MM Cheng |
| Title |
Endpoints Weight Fusion for Class Incremental Semantic Segmentation |
Type |
Conference Article |
| Year |
2023 |
Publication |
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
7204-7213 |
| Keywords |
|
| Abstract |
Class incremental semantic segmentation (CISS) focuses on alleviating catastrophic forgetting to improve discrimination. Previous work mainly exploit regularization (e.g., knowledge distillation) to maintain previous knowledge in the current model. However, distillation alone often yields limited gain to the model since only the representations of old and new models are restricted to be consistent. In this paper, we propose a simple yet effective method to obtain a model with strong memory of old knowledge, named Endpoints Weight Fusion (EWF). In our method, the model containing old knowledge is fused with the model retaining new knowledge in a dynamic fusion manner, strengthening the memory of old classes in ever-changing distributions. In addition, we analyze the relation between our fusion strategy and a popular moving average technique EMA, which reveals why our method is more suitable for class-incremental learning. To facilitate parameter fusion with closer distance in the parameter space, we use distillation to enhance the optimization process. Furthermore, we conduct experiments on two widely used datasets, achieving the state-of-the-art performance. |
| Address |
Vancouver; Canada; June 2023 |
| 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 |
Approved |
no |
| Call Number |
Admin @ si @ XZF2023 |
Serial |
3854 |
| Permanent link to this record |
| |
|
| |
| Author |
Akshita Gupta; Sanath Narayan; Salman Khan; Fahad Shahbaz Khan; Ling Shao; Joost Van de Weijer |
| Title |
Generative Multi-Label Zero-Shot Learning |
Type |
Journal Article |
| Year |
2023 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
| Volume |
45 |
Issue |
12 |
Pages |
14611-14624 |
| Keywords |
Generalized zero-shot learning; Multi-label classification; Zero-shot object detection; Feature synthesis |
| Abstract |
Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention from the seen classes. Nevertheless, computing reliable attention maps for unseen classes during inference in a multi-label setting is still a challenge. In contrast, state-of-the-art single-label generative adversarial network (GAN) based approaches learn to directly synthesize the class-specific visual features from the corresponding class attribute embeddings. However, synthesizing multi-label features from GANs is still unexplored in the context of zero-shot setting. When multiple objects occur jointly in a single image, a critical question is how to effectively fuse multi-class information. In this work, we introduce different fusion approaches at the attribute-level, feature-level and cross-level (across attribute and feature-levels) for synthesizing multi-label features from their corresponding multi-label class embeddings. To the best of our knowledge, our work is the first to tackle the problem of multi-label feature synthesis in the (generalized) zero-shot setting. Our cross-level fusion-based generative approach outperforms the state-of-the-art on three zero-shot benchmarks: NUS-WIDE, Open Images and MS COCO. Furthermore, we show the generalization capabilities of our fusion approach in the zero-shot detection task on MS COCO, achieving favorable performance against existing methods. |
| Address |
December 2023 |
| 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; PID2021-128178OB-I00 |
Approved |
no |
| Call Number |
Admin @ si @ |
Serial |
3853 |
| Permanent link to this record |
| |
|
| |
| Author |
Mickael Coustaty; Alicia Fornes |
| Title |
Document Analysis and Recognition – ICDAR 2023 Workshops |
Type |
Book Whole |
| Year |
2023 |
Publication |
Document Analysis and Recognition – ICDAR 2023 Workshops |
Abbreviated Journal |
|
| Volume |
14194 |
Issue |
2 |
Pages |
|
| Keywords |
|
| Abstract |
|
| Address |
San Jose; USA; August 2023 |
| Corporate Author |
|
Thesis |
|
| Publisher |
|
Place of Publication |
|
Editor |
|
| Language |
|
Summary Language |
|
Original Title |
|
| Series Editor |
|
Series Title |
|
Abbreviated Series Title |
LNCS |
| Series Volume |
|
Series Issue |
|
Edition |
|
| ISSN |
|
ISBN |
|
Medium |
|
| Area |
|
Expedition |
|
Conference |
ICDAR |
| Notes |
DAG |
Approved |
no |
| Call Number |
Admin @ si @ CoF2023 |
Serial |
3852 |
| Permanent link to this record |
| |
|
| |
| Author |
Marwa Dhiaf; Mohamed Ali Souibgui; Kai Wang; Yuyang Liu; Yousri Kessentini; Alicia Fornes; Ahmed Cheikh Rouhou |
| Title |
CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition |
Type |
Miscellaneous |
| Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
|
| Keywords |
|
| Abstract |
Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, where data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance on English, Italian and Russian scripts, whilst adding only a few parameters per task. The code and trained models will be publicly available. |
| 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 |
DAG |
Approved |
no |
| Call Number |
Admin @ si @ DSW2023 |
Serial |
3851 |
| Permanent link to this record |
