| Home | << 1 2 3 4 5 6 7 8 9 10 >> [11–11] |
|
| Records | |||||
|---|---|---|---|---|---|
| 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 | 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 | Pau Torras; Mohamed Ali Souibgui; Sanket Biswas; Alicia Fornes | ||||
| Title | Segmentation-Free Alignment of Arbitrary Symbol Transcripts to Images | Type | Conference Article | ||
| Year | 2023 | Publication |
Document Analysis and Recognition – ICDAR 2023 Workshops | Abbreviated Journal | |
| Volume | 14193 | Issue | Pages | 83-93 | |
| Keywords | Historical Manuscripts; Symbol Alignment | ||||
| Abstract | Developing arbitrary symbol recognition systems is a challenging endeavour. Even using content-agnostic architectures such as few-shot models, performance can be substantially improved by providing a number of well-annotated examples into training. In some contexts, transcripts of the symbols are available without any position information associated to them, which enables using line-level recognition architectures. A way of providing this position information to detection-based architectures is finding systems that can align the input symbols with the transcription. In this paper we discuss some symbol alignment techniques that are suitable for low-data scenarios and provide an insight on their perceived strengths and weaknesses. In particular, we study the usage of Connectionist Temporal Classification models, Attention-Based Sequence to Sequence models and we compare them with the results obtained on a few-shot recognition system. | ||||
| Address | |||||
| 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 @ TSS2023 | Serial | 3850 | ||
| Permanent link to this record | |||||
| Author | P. Canals; Simone Balocco; O. Diaz; J. Li; A. Garcia Tornel; M. Olive Gadea; M. Ribo | ||||
| Title | A fully automatic method for vascular tortuosity feature extraction in the supra-aortic region: unraveling possibilities in stroke treatment planning | Type | Journal Article | ||
| Year | 2023 | Publication |
Computerized Medical Imaging and Graphics | Abbreviated Journal | CMIG |
| Volume | 104 | Issue | 102170 | Pages | |
| Keywords | Artificial intelligence; Deep learning; Stroke; Thrombectomy; Vascular feature extraction; Vascular tortuosity | ||||
| Abstract | Vascular tortuosity of supra-aortic vessels is widely considered one of the main reasons for failure and delays in endovascular treatment of large vessel occlusion in patients with acute ischemic stroke. Characterization of tortuosity is a challenging task due to the lack of objective, robust and effective analysis tools. We present a fully automatic method for arterial segmentation, vessel labelling and tortuosity feature extraction applied to the supra-aortic region. A sample of 566 computed tomography angiography scans from acute ischemic stroke patients (aged 74.8 ± 12.9, 51.0% females) were used for training, validation and testing of a segmentation module based on a U-Net architecture (162 cases) and a vessel labelling module powered by a graph U-Net (566 cases). Successively, 30 cases were processed for testing of a tortuosity feature extraction module. Measurements obtained through automatic processing were compared to manual annotations from two observers for a thorough validation of the method. The proposed feature extraction method presented similar performance to the inter-rater variability observed in the measurement of 33 geometrical and morphological features of the arterial anatomy in the supra-aortic region. This system will contribute to the development of more complex models to advance the treatment of stroke by adding immediate automation, objectivity, repeatability and robustness to the vascular tortuosity characterization of patients. | ||||
| 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 @ CBD2023 | Serial | 4005 | ||
| Permanent link to this record | |||||
| Author | Shiqi Yang; Yaxing Wang; Luis Herranz; Shangling Jui; Joost Van de Weijer | ||||
| Title | Casting a BAIT for offline and online source-free domain adaptation | Type | Journal Article | ||
| Year | 2023 | Publication |
Computer Vision and Image Understanding | Abbreviated Journal | CVIU |
| Volume | 234 | Issue | Pages | 103747 | |
| Keywords | |||||
| Abstract | We address the source-free domain adaptation (SFDA) problem, where only the source model is available during adaptation to the target domain. We consider two settings: the offline setting where all target data can be visited multiple times (epochs) to arrive at a prediction for each target sample, and the online setting where the target data needs to be directly classified upon arrival. Inspired by diverse classifier based domain adaptation methods, in this paper we introduce a second classifier, but with another classifier head fixed. When adapting to the target domain, the additional classifier initialized from source classifier is expected to find misclassified features. Next, when updating the feature extractor, those features will be pushed towards the right side of the source decision boundary, thus achieving source-free domain adaptation. Experimental results show that the proposed method achieves competitive results for offline SFDA on several benchmark datasets compared with existing DA and SFDA methods, and our method surpasses by a large margin other SFDA methods under online source-free domain adaptation setting. | ||||
| 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; MACO | Approved | no | ||
| Call Number | Admin @ si @ YWH2023 | Serial | 3874 | ||
| Permanent link to this record | |||||
| Author | Juan Borrego-Carazo; Carles Sanchez; David Castells; Jordi Carrabina; Debora Gil | ||||
| Title | BronchoPose: an analysis of data and model configuration for vision-based bronchoscopy pose estimation | Type | Journal Article | ||
| Year | 2023 | Publication |
Computer Methods and Programs in Biomedicine | Abbreviated Journal | CMPB |
| Volume | 228 | Issue | Pages | 107241 | |
| Keywords | Videobronchoscopy guiding; Deep learning; Architecture optimization; Datasets; Standardized evaluation framework; Pose estimation | ||||
| Abstract | Vision-based bronchoscopy (VB) models require the registration of the virtual lung model with the frames from the video bronchoscopy to provide effective guidance during the biopsy. The registration can be achieved by either tracking the position and orientation of the bronchoscopy camera or by calibrating its deviation from the pose (position and orientation) simulated in the virtual lung model. Recent advances in neural networks and temporal image processing have provided new opportunities for guided bronchoscopy. However, such progress has been hindered by the lack of comparative experimental conditions.
In the present paper, we share a novel synthetic dataset allowing for a fair comparison of methods. Moreover, this paper investigates several neural network architectures for the learning of temporal information at different levels of subject personalization. In order to improve orientation measurement, we also present a standardized comparison framework and a novel metric for camera orientation learning. Results on the dataset show that the proposed metric and architectures, as well as the standardized conditions, provide notable improvements to current state-of-the-art camera pose estimation in video bronchoscopy. |
||||
| Address | |||||
| Corporate Author | Thesis | ||||
| Publisher | Elsevier | 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 @ BSC2023 | Serial | 3702 | ||
| Permanent link to this record | |||||
| Author | Danna Xue; Javier Vazquez; Luis Herranz; Yang Zhang; Michael S Brown | ||||
| Title | Integrating High-Level Features for Consistent Palette-based Multi-image Recoloring | Type | Journal Article | ||
| Year | 2023 | Publication |
Computer Graphics Forum | Abbreviated Journal | CGF |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Achieving visually consistent colors across multiple images is important when images are used in photo albums, websites, and brochures. Unfortunately, only a handful of methods address multi-image color consistency compared to one-to-one color transfer techniques. Furthermore, existing methods do not incorporate high-level features that can assist graphic designers in their work. To address these limitations, we introduce a framework that builds upon a previous palette-based color consistency method and incorporates three high-level features: white balance, saliency, and color naming. We show how these features overcome the limitations of the prior multi-consistency workflow and showcase the user-friendly nature of our framework. | ||||
| 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 | CIC; MACO | Approved | no | ||
| Call Number | Admin @ si @ XVH2023 | Serial | 3883 | ||
| 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 | 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 | |||||
| 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 | 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 | 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 | David Pujol Perich; Albert Clapes; Sergio Escalera | ||||
| Title | SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization | Type | Miscellaneous | ||
| Year | 2023 | Publication |
Arxiv | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, are often neglected in the literature, exposing these solutions to important performance degradation. In this work, we tackle this issue by introducing, for the first time, an approach for Unsupervised Domain Adaptation (UDA) in sparse TAL, which we refer to as Semantic Adversarial unsupervised Domain Adaptation (SADA). Our contributions are threefold: (1) we pioneer the development of a domain adaptation model that operates on realistic sparse action detection benchmarks; (2) we tackle the limitations of global-distribution alignment techniques by introducing a novel adversarial loss that is sensitive to local class distributions, ensuring finer-grained adaptation; and (3) we present a novel set of benchmarks based on EpicKitchens100 and CharadesEgo, that evaluate multiple domain shifts in a comprehensive manner. Our experiments indicate that SADA improves the adaptation across domains when compared to fully supervised state-of-the-art and alternative UDA methods, attaining a performance boost of up to 6.14% mAP. | ||||
| 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 | HUPBA | Approved | no | ||
| Call Number | Admin @ si @ PCE2023 | Serial | 4014 | ||
| Permanent link to this record | |||||
| Author | Senmao Li; Joost van de Weijer; Taihang Hu; Fahad Shahbaz Khan; Qibin Hou; Yaxing Wang; Jian Yang | ||||
| Title | StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing | Type | Miscellaneous | ||
| Year | 2023 | Publication |
Arxiv | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | A significant research effort is focused on exploiting the amazing capacities of pretrained diffusion models for the editing of images. They either finetune the model, or invert the image in the latent space of the pretrained model. However, they suffer from two problems: (1) Unsatisfying results for selected regions, and unexpected changes in nonselected regions. (2) They require careful text prompt editing where the prompt should include all visual objects in the input image. To address this, we propose two improvements: (1) Only optimizing the input of the value linear network in the cross-attention layers, is sufficiently powerful to reconstruct a real image. (2) We propose attention regularization to preserve the object-like attention maps after editing, enabling us to obtain accurate style editing without invoking significant structural changes. We further improve the editing technique which is used for the unconditional branch of classifier-free guidance, as well as the conditional one as used by P2P. Extensive experimental prompt-editing results on a variety of images, demonstrate qualitatively and quantitatively that our method has superior editing capabilities than existing and concurrent works. | ||||
| 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 | Approved | no | ||
| Call Number | Admin @ si @ LWH2023 | Serial | 3870 | ||
| Permanent link to this record | |||||
| Author | Antonio Carta; Andrea Cossu; Vincenzo Lomonaco; Davide Bacciu; Joost Van de Weijer | ||||
| Title | Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual Learning | Type | Miscellaneous | ||
| Year | 2023 | Publication |
Arxiv | Abbreviated Journal | |
| Volume | Issue | Pages | |||
| Keywords | |||||
| Abstract | Distributed learning on the edge often comprises self-centered devices (SCD) which learn local tasks independently and are unwilling to contribute to the performance of other SDCs. How do we achieve forward transfer at zero cost for the single SCDs? We formalize this problem as a Distributed Continual Learning scenario, where SCD adapt to local tasks and a CL model consolidates the knowledge from the resulting stream of models without looking at the SCD's private data. Unfortunately, current CL methods are not directly applicable to this scenario. We propose Data-Agnostic Consolidation (DAC), a novel double knowledge distillation method that consolidates the stream of SC models without using the original data. DAC performs distillation in the latent space via a novel Projected Latent Distillation loss. Experimental results show that DAC enables forward transfer between SCDs and reaches state-of-the-art accuracy on Split CIFAR100, CORe50 and Split TinyImageNet, both in reharsal-free and distributed CL scenarios. Somewhat surprisingly, even a single out-of-distribution image is sufficient as the only source of data during consolidation. | ||||
| 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 | Approved | no | ||
| Call Number | Admin @ si @ CCL2023 | Serial | 3871 | ||
| Permanent link to this record | |||||