Home | [81–90] << 91 92 93 94 95 96 97 98 99 100 >> [101–110] |
![]() |
Records | |||||
---|---|---|---|---|---|
Author | Marc Masana; Bartlomiej Twardowski; Joost Van de Weijer | ||||
Title | On Class Orderings for Incremental Learning | Type | Conference Article | ||
Year | 2020 | Publication | ICML Workshop on Continual Learning | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | The influence of class orderings in the evaluation of incremental learning has received very little attention. In this paper, we investigate the impact of class orderings for incrementally learned classifiers. We propose a method to compute various orderings for a dataset. The orderings are derived by simulated annealing optimization from the confusion matrix and reflect different incremental learning scenarios, including maximally and minimally confusing tasks. We evaluate a wide range of state-of-the-art incremental learning methods on the proposed orderings. Results show that orderings can have a significant impact on performance and the ranking of the methods. | ||||
Address | Virtual; July 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 | ICMLW | ||
Notes | LAMP; 600.120 | Approved | no | ||
Call Number ![]() |
Admin @ si @ MTW2020 | Serial | 3505 | ||
Permanent link to this record | |||||
Author | Marc Masana; Tinne Tuytelaars; Joost Van de Weijer | ||||
Title | Ternary Feature Masks: zero-forgetting for task-incremental learning | Type | Conference Article | ||
Year | 2021 | Publication | 34th IEEE Conference on Computer Vision and Pattern Recognition Workshops | Abbreviated Journal | |
Volume | Issue | Pages | 3565-3574 | ||
Keywords | |||||
Abstract | We propose an approach without any forgetting to continual learning for the task-aware regime, where at inference the task-label is known. By using ternary masks we can upgrade a model to new tasks, reusing knowledge from previous tasks while not forgetting anything about them. Using masks prevents both catastrophic forgetting and backward transfer. We argue -- and show experimentally -- that avoiding the former largely compensates for the lack of the latter, which is rarely observed in practice. In contrast to earlier works, our masks are applied to the features (activations) of each layer instead of the weights. This considerably reduces the number of mask parameters for each new task; with more than three orders of magnitude for most networks. The encoding of the ternary masks into two bits per feature creates very little overhead to the network, avoiding scalability issues. To allow already learned features to adapt to the current task without changing the behavior of these features for previous tasks, we introduce task-specific feature normalization. Extensive experiments on several finegrained datasets and ImageNet show that our method outperforms current state-of-the-art while reducing memory overhead in comparison to weight-based approaches. | ||||
Address | Virtual; June 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 | CVPRW | ||
Notes | LAMP; 600.120 | Approved | no | ||
Call Number ![]() |
Admin @ si @ MTW2021 | Serial | 3565 | ||
Permanent link to this record | |||||
Author | Naila Murray | ||||
Title | Perceptual Feature Detection | Type | Report | ||
Year | 2009 | Publication | CVC Technical Report | Abbreviated Journal | |
Volume | 131 | Issue | Pages | ||
Keywords | |||||
Abstract | |||||
Address | |||||
Corporate Author | Computer Vision Center | Thesis | Master's thesis | ||
Publisher | Place of Publication | Bellaterra, Barcelona | 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 | Approved | no | ||
Call Number ![]() |
Admin @ si @ Mur2009 | Serial | 2390 | ||
Permanent link to this record | |||||
Author | Naila Murray | ||||
Title | Predicting Saliency and Aesthetics in Images: A Bottom-up Perspective | Type | Book Whole | ||
Year | 2012 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | In Part 1 of the thesis, we hypothesize that salient and non-salient image regions can be estimated to be the regions which are enhanced or assimilated in standard low-level color image representations. We prove this hypothesis by adapting a low-level model of color perception into a saliency estimation model. This model shares the three main steps found in many successful models for predicting attention in a scene: convolution with a set of filters, a center-surround mechanism and spatial pooling to construct a saliency map. For such models, integrating spatial information and justifying the choice of various parameter values remain open problems. Our saliency model inherits a principled selection of parameters as well as an innate spatial pooling mechanism from the perception model on which it is based. This pooling mechanism has been fitted using psychophysical data acquired in color-luminance setting experiments. The proposed model outperforms the state-of-the-art at the task of predicting eye-fixations from two datasets. After demonstrating the effectiveness of our basic saliency model, we introduce an improved image representation, based on geometrical grouplets, that enhances complex low-level visual features such as corners and terminations, and suppresses relatively simpler features such as edges. With this improved image representation, the performance of our saliency model in predicting eye-fixations increases for both datasets.
In Part 2 of the thesis, we investigate the problem of aesthetic visual analysis. While a great deal of research has been conducted on hand-crafting image descriptors for aesthetics, little attention so far has been dedicated to the collection, annotation and distribution of ground truth data. Because image aesthetics is complex and subjective, existing datasets, which have few images and few annotations, have significant limitations. To address these limitations, we have introduced a new large-scale database for conducting Aesthetic Visual Analysis, which we call AVA. AVA contains more than 250,000 images, along with a rich variety of annotations. We investigate how the wealth of data in AVA can be used to tackle the challenge of understanding and assessing visual aesthetics by looking into several problems relevant for aesthetic analysis. We demonstrate that by leveraging the data in AVA, and using generic low-level features such as SIFT and color histograms, we can exceed state-of-the-art performance in aesthetic quality prediction tasks. Finally, we entertain the hypothesis that low-level visual information in our saliency model can also be used to predict visual aesthetics by capturing local image characteristics such as feature contrast, grouping and isolation, characteristics thought to be related to universal aesthetic laws. We use the weighted center-surround responses that form the basis of our saliency model to create a feature vector that describes aesthetics. We also introduce a novel color space for fine-grained color representation. We then demonstrate that the resultant features achieve state-of-the-art performance on aesthetic quality classification. As such, a promising contribution of this thesis is to show that several vision experiences – low-level color perception, visual saliency and visual aesthetics estimation – may be successfully modeled using a unified framework. This suggests a similar architecture in area V1 for both color perception and saliency and adds evidence to the hypothesis that visual aesthetics appreciation is driven in part by low-level cues. |
||||
Address | |||||
Corporate Author | Thesis | Ph.D. thesis | |||
Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Xavier Otazu;Maria Vanrell | |
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 | Approved | no | ||
Call Number ![]() |
Admin @ si @ Mur2012 | Serial | 2212 | ||
Permanent link to this record | |||||
Author | Naila Murray; Eduard Vazquez | ||||
Title | Lacuna Restoration: How to choose a neutral colour? | Type | Conference Article | ||
Year | 2010 | Publication | Proceedings of The CREATE 2010 Conference | Abbreviated Journal | |
Volume | Issue | Pages | 248–252 | ||
Keywords | |||||
Abstract | Painting restoration which involves filling in material loss (called lacuna) is a complex process. Several standard techniques exist to tackle lacuna restoration,
and this article focuses on those techniques that employ a “neutral” colour to mask the defect. Restoration experts often disagree on the choice of such a colour and in fact, the concept of a neutral colour is controversial. We posit that a neutral colour is one that attracts relatively little visual attention for a specific lacuna. We conducted an eye tracking experiment to compare two common neutral colour selection methods, specifically the most common local colour and the mean local colour. Results obtained demonstrate that the most common local colour triggers less visual attention in general. Notwithstanding, we have observed instances in which the most common colour triggers a significant amount of attention when subjects spent time resolving their confusion about whether or not a lacuna was part of the painting. |
||||
Address | Gjovik, Norway | ||||
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 | CREATE | ||
Notes | CIC | Approved | no | ||
Call Number ![]() |
Admin @ si @ MuV2010 | Serial | 1297 | ||
Permanent link to this record | |||||
Author | Lasse Martensson; Ekta Vats; Anders Hast; Alicia Fornes | ||||
Title | In Search of the Scribe: Letter Spotting as a Tool for Identifying Scribes in Large Handwritten Text Corpora | Type | Journal | ||
Year | 2019 | Publication | Journal for Information Technology Studies as a Human Science | Abbreviated Journal | HUMAN IT |
Volume | 14 | Issue | 2 | Pages | 95-120 |
Keywords | Scribal attribution/ writer identification; digital palaeography; word spotting; mediaeval charters; mediaeval manuscripts | ||||
Abstract | In this article, a form of the so-called word spotting-method is used on a large set of handwritten documents in order to identify those that contain script of similar execution. The point of departure for the investigation is the mediaeval Swedish manuscript Cod. Holm. D 3. The main scribe of this manuscript has yet not been identified in other documents. The current attempt aims at localising other documents that display a large degree of similarity in the characteristics of the script, these being possible candidates for being executed by the same hand. For this purpose, the method of word spotting has been employed, focusing on individual letters, and therefore the process is referred to as letter spotting in the article. In this process, a set of ‘g’:s, ‘h’:s and ‘k’:s have been selected as templates, and then a search has been made for close matches among the mediaeval Swedish charters. The search resulted in a number of charters that displayed great similarities with the manuscript D 3. The used letter spotting method thus proofed to be a very efficient sorting tool localising similar script samples. | ||||
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; 600.097; 600.140; 600.121 | Approved | no | ||
Call Number ![]() |
Admin @ si @ MVH2019 | Serial | 3234 | ||
Permanent link to this record | |||||
Author | Helena Muñoz; Fernando Vilariño; Dimosthenis Karatzas | ||||
Title | Eye-Movements During Information Extraction from Administrative Documents | Type | Conference Article | ||
Year | 2019 | Publication | International Conference on Document Analysis and Recognition Workshops | Abbreviated Journal | |
Volume | Issue | Pages | 6-9 | ||
Keywords | |||||
Abstract | A key aspect of digital mailroom processes is the extraction of relevant information from administrative documents. More often than not, the extraction process cannot be fully automated, and there is instead an important amount of manual intervention. In this work we study the human process of information extraction from invoice document images. We explore whether the gaze of human annotators during an manual information extraction process could be exploited towards reducing the manual effort and automating the process. To this end, we perform an eye-tracking experiment replicating real-life interfaces for information extraction. Through this pilot study we demonstrate that relevant areas in the document can be identified reliably through automatic fixation classification, and the obtained models generalize well to new subjects. Our findings indicate that it is in principle possible to integrate the human in the document image analysis loop, making use of the scanpath to automate the extraction process or verify extracted information. | ||||
Address | Sydney; Australia; September 2019 | ||||
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 | ICDARW | ||
Notes | DAG; 600.140; 600.121; 600.129;SIAI | Approved | no | ||
Call Number ![]() |
Admin @ si @ MVK2019 | Serial | 3336 | ||
Permanent link to this record | |||||
Author | Naila Murray; Maria Vanrell; Xavier Otazu; C. Alejandro Parraga | ||||
Title | Saliency Estimation Using a Non-Parametric Low-Level Vision Model | Type | Conference Article | ||
Year | 2011 | Publication | IEEE conference on Computer Vision and Pattern Recognition | Abbreviated Journal | |
Volume | Issue | Pages | 433-440 | ||
Keywords | Gaussian mixture model;ad hoc parameter selection;center-surround inhibition windows;center-surround mechanism;color appearance model;convolution;eye-fixation data;human vision;innate spatial pooling mechanism;inverse wavelet transform;low-level visual front-end;nonparametric low-level vision model;saliency estimation;saliency map;scale integration;scale-weighted center-surround response;scale-weighting function;visual task;Gaussian processes;biology;biology computing;colour vision;computer vision;visual perception;wavelet transforms | ||||
Abstract | Many successful models for predicting attention in a scene involve three main steps: convolution with a set of filters, a center-surround mechanism and spatial pooling to construct a saliency map. However, integrating spatial information and justifying the choice of various parameter values remain open problems. In this paper we show that an efficient model of color appearance in human vision, which contains a principled selection of parameters as well as an innate spatial pooling mechanism, can be generalized to obtain a saliency model that outperforms state-of-the-art models. Scale integration is achieved by an inverse wavelet transform over the set of scale-weighted center-surround responses. The scale-weighting function (termed ECSF) has been optimized to better replicate psychophysical data on color appearance, and the appropriate sizes of the center-surround inhibition windows have been determined by training a Gaussian Mixture Model on eye-fixation data, thus avoiding ad-hoc parameter selection. Additionally, we conclude that the extension of a color appearance model to saliency estimation adds to the evidence for a common low-level visual front-end for different visual tasks. | ||||
Address | Colorado Springs | ||||
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 | 1063-6919 | ISBN | 978-1-4577-0394-2 | Medium | |
Area | Expedition | Conference | CVPR | ||
Notes | CIC | Approved | no | ||
Call Number ![]() |
Admin @ si @ MVO2011 | Serial | 1757 | ||
Permanent link to this record | |||||
Author | Naila Murray; Maria Vanrell; Xavier Otazu; C. Alejandro Parraga | ||||
Title | Low-level SpatioChromatic Grouping for Saliency Estimation | Type | Journal Article | ||
Year | 2013 | Publication | IEEE Transactions on Pattern Analysis and Machine Intelligence | Abbreviated Journal | TPAMI |
Volume | 35 | Issue | 11 | Pages | 2810-2816 |
Keywords | |||||
Abstract | We propose a saliency model termed SIM (saliency by induction mechanisms), which is based on a low-level spatiochromatic model that has successfully predicted chromatic induction phenomena. In so doing, we hypothesize that the low-level visual mechanisms that enhance or suppress image detail are also responsible for making some image regions more salient. Moreover, SIM adds geometrical grouplets to enhance complex low-level features such as corners, and suppress relatively simpler features such as edges. Since our model has been fitted on psychophysical chromatic induction data, it is largely nonparametric. SIM outperforms state-of-the-art methods in predicting eye fixations on two datasets and using two metrics. | ||||
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 | 0162-8828 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | CIC; 600.051; 600.052; 605.203 | Approved | no | ||
Call Number ![]() |
Admin @ si @ MVO2013 | Serial | 2289 | ||
Permanent link to this record | |||||
Author | Mikhail Mozerov; Fei Yang; Joost Van de Weijer | ||||
Title | Sparse Data Interpolation Using the Geodesic Distance Affinity Space | Type | Journal Article | ||
Year | 2019 | Publication | IEEE Signal Processing Letters | Abbreviated Journal | SPL |
Volume | 26 | Issue | 6 | Pages | 943 - 947 |
Keywords | |||||
Abstract | In this letter, we adapt the geodesic distance-based recursive filter to the sparse data interpolation problem. The proposed technique is general and can be easily applied to any kind of sparse data. We demonstrate its superiority over other interpolation techniques in three experiments for qualitative and quantitative evaluation. In addition, we compare our method with the popular interpolation algorithm presented in the paper on EpicFlow optical flow, which is intuitively motivated by a similar geodesic distance principle. The comparison shows that our algorithm is more accurate and considerably faster than the EpicFlow interpolation technique. | ||||
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 | Approved | no | ||
Call Number ![]() |
Admin @ si @ MYW2019 | Serial | 3261 | ||
Permanent link to this record | |||||
Author | Naveen Onkarappa; Angel Sappa | ||||
Title | An Empirical Study on Optical Flow Accuracy Depending on Vehicle Speed | Type | Conference Article | ||
Year | 2012 | Publication | IEEE Intelligent Vehicles Symposium | Abbreviated Journal | |
Volume | Issue | Pages | 1138-1143 | ||
Keywords | |||||
Abstract | Driver assistance and safety systems are getting attention nowadays towards automatic navigation and safety. Optical flow as a motion estimation technique has got major roll in making these systems a reality. Towards this, in the current paper, the suitability of polar representation for optical flow estimation in such systems is demonstrated. Furthermore, the influence of individual regularization terms on the accuracy of optical flow on image sequences of different speeds is empirically evaluated. Also a new synthetic dataset of image sequences with different speeds is generated along with the ground-truth optical flow. | ||||
Address | Alcalá de Henares | ||||
Corporate Author | Thesis | ||||
Publisher | IEEE Xplore | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 1931-0587 | ISBN | 978-1-4673-2119-8 | Medium | |
Area | Expedition | Conference | IV | ||
Notes | ADAS | Approved | no | ||
Call Number ![]() |
Admin @ si @ NaS2012 | Serial | 2020 | ||
Permanent link to this record | |||||
Author | M. Navarro | ||||
Title | Reconeixement d´objectes amb metodes basats en color: avaluacio en un entorn poc controlat | Type | Report | ||
Year | 1999 | Publication | CVC Technical Report #28 | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | |||||
Address | CVC (UAB) | ||||
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 | Approved | no | |||
Call Number ![]() |
Admin @ si @ Nav1999 | Serial | 190 | ||
Permanent link to this record | |||||
Author | Naveen Onkarappa | ||||
Title | Optical Flow in Driver Assistance Systems | Type | Book Whole | ||
Year | 2013 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract | Motion perception is one of the most important attributes of the human brain. Visual motion perception consists in inferring speed and direction of elements in a scene based on visual inputs. Analogously, computer vision is assisted by motion cues in the scene. Motion detection in computer vision is useful in solving problems such as segmentation, depth from motion, structure from motion, compression, navigation and many others. These problems are common in several applications, for instance, video surveillance, robot navigation and advanced driver assistance systems (ADAS). One of the most widely used techniques for motion detection is the optical flow estimation. The work in this thesis attempts to make optical flow suitable for the requirements and conditions of driving scenarios. In this context, a novel space-variant representation called reverse log-polar representation is proposed that is shown to be better than the traditional log-polar space-variant representation for ADAS. The space-variant representations reduce the amount of data to be processed. Another major contribution in this research is related to the analysis of the influence of specific characteristics from driving scenarios on the optical flow accuracy. Characteristics such as vehicle speed and
road texture are considered in the aforementioned analysis. From this study, it is inferred that the regularization weight has to be adapted according to the required error measure and for different speeds and road textures. It is also shown that polar represented optical flow suits driving scenarios where predominant motion is translation. Due to the requirements of such a study and by the lack of needed datasets a new synthetic dataset is presented; it contains: i) sequences of different speeds and road textures in an urban scenario; ii) sequences with complex motion of an on-board camera; and iii) sequences with additional moving vehicles in the scene. The ground-truth optical flow is generated by the ray-tracing technique. Further, few applications of optical flow in ADAS are shown. Firstly, a robust RANSAC based technique to estimate horizon line is proposed. Then, an egomotion estimation is presented to compare the proposed space-variant representation with the classical one. As a final contribution, a modification in the regularization term is proposed that notably improves the results in the ADAS applications. This adaptation is evaluated using a state of the art optical flow technique. The experiments on a public dataset (KITTI) validate the advantages of using the proposed modification. |
||||
Address | Bellaterra | ||||
Corporate Author | Thesis | Ph.D. thesis | |||
Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Angel Sappa | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-84-940902-1-9 | Medium | ||
Area | Expedition | Conference | |||
Notes | ADAS | Approved | no | ||
Call Number ![]() |
Admin @ si @ Nav2013 | Serial | 2447 | ||
Permanent link to this record | |||||
Author | Mohammad Naser Sabet; Pau Buch Cardona; Egils Avots; Kamal Nasrollahi; Sergio Escalera; Thomas B. Moeslund; Gholamreza Anbarjafari | ||||
Title | Privacy-Constrained Biometric System for Non-cooperative Users | Type | Journal Article | ||
Year | 2019 | Publication | Entropy | Abbreviated Journal | ENTROPY |
Volume | 21 | Issue | 11 | Pages | 1033 |
Keywords | biometric recognition; multimodal-based human identification; privacy; deep learning | ||||
Abstract | With the consolidation of the new data protection regulation paradigm for each individual within the European Union (EU), major biometric technologies are now confronted with many concerns related to user privacy in biometric deployments. When individual biometrics are disclosed, the sensitive information about his/her personal data such as financial or health are at high risk of being misused or compromised. This issue can be escalated considerably over scenarios of non-cooperative users, such as elderly people residing in care homes, with their inability to interact conveniently and securely with the biometric system. The primary goal of this study is to design a novel database to investigate the problem of automatic people recognition under privacy constraints. To do so, the collected data-set contains the subject’s hand and foot traits and excludes the face biometrics of individuals in order to protect their privacy. We carried out extensive simulations using different baseline methods, including deep learning. Simulation results show that, with the spatial features extracted from the subject sequence in both individual hand or foot videos, state-of-the-art deep models provide promising recognition performance. | ||||
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; no proj | Approved | no | ||
Call Number ![]() |
Admin @ si @ NBA2019 | Serial | 3313 | ||
Permanent link to this record | |||||
Author | Bhalaji Nagarajan; Marc Bolaños; Eduardo Aguilar; Petia Radeva | ||||
Title | Deep ensemble-based hard sample mining for food recognition | Type | Journal Article | ||
Year | 2023 | Publication | Journal of Visual Communication and Image Representation | Abbreviated Journal | JVCIR |
Volume | 95 | Issue | Pages | 103905 | |
Keywords | |||||
Abstract | Deep neural networks represent a compelling technique to tackle complex real-world problems, but are over-parameterized and often suffer from over- or under-confident estimates. Deep ensembles have shown better parameter estimations and often provide reliable uncertainty estimates that contribute to the robustness of the results. In this work, we propose a new metric to identify samples that are hard to classify. Our metric is defined as coincidence score for deep ensembles which measures the agreement of its individual models. The main hypothesis we rely on is that deep learning algorithms learn the low-loss samples better compared to large-loss samples. In order to compensate for this, we use controlled over-sampling on the identified ”hard” samples using proper data augmentation schemes to enable the models to learn those samples better. We validate the proposed metric using two public food datasets on different backbone architectures and show the improvements compared to the conventional deep neural network training using different performance metrics. | ||||
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 @ NBA2023 | Serial | 3844 | ||
Permanent link to this record |