Home << 1 2 >>
List View
 | 
Citations
 | 
Details
   web
Records
Author Marcos V Conde; Javier Vazquez; Michael S Brown; Radu TImofte
Title NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement Type Conference Article
Year 2024 Publication 38th AAAI Conference on Artificial Intelligence Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) 3D lookup tables (3D LUTs) are a key component for image enhancement. Modern image signal processors (ISPs) have dedicated support for these as part of the camera rendering pipeline. Cameras typically provide multiple options for picture styles, where each style is usually obtained by applying a unique handcrafted 3D LUT. Current approaches for learning and applying 3D LUTs are notably fast, yet not so memory-efficient, as storing multiple 3D LUTs is required. For this reason and other implementation limitations, their use on mobile devices is less popular. In this work, we propose a Neural Implicit LUT (NILUT), an implicitly defined continuous 3D color transformation parameterized by a neural network. We show that NILUTs are capable of accurately emulating real 3D LUTs. Moreover, a NILUT can be extended to incorporate multiple styles into a single network with the ability to blend styles implicitly. Our novel approach is memory-efficient, controllable and can complement previous methods, including learned ISPs.
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 AAAI
Notes CIC; MACO Approved no
Call Number Admin @ si @ CVB2024 Serial 3872
Permanent link to this record
 
 
Author Vacit Oguz Yazici; Longlong Yu; Arnau Ramisa; Luis Herranz; Joost Van de Weijer
Title Main product detection with graph networks for fashion Type Journal Article
Year 2024 Publication Multimedia Tools and Applications Abbreviated Journal MTAP
Volume 83 Issue Pages 3215–3231
Keywords
Abstract (up) Computer vision has established a foothold in the online fashion retail industry. Main product detection is a crucial step of vision-based fashion product feed parsing pipelines, focused on identifying the bounding boxes that contain the product being sold in the gallery of images of the product page. The current state-of-the-art approach does not leverage the relations between regions in the image, and treats images of the same product independently, therefore not fully exploiting visual and product contextual information. In this paper, we propose a model that incorporates Graph Convolutional Networks (GCN) that jointly represent all detected bounding boxes in the gallery as nodes. We show that the proposed method is better than the state-of-the-art, especially, when we consider the scenario where title-input is missing at inference time and for cross-dataset evaluation, our method outperforms previous approaches by a large margin.
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; 600.147; 600.167; 600.164; 600.161; 600.141; 601.309 Approved no
Call Number Admin @ si @ YYR2024 Serial 4017
Permanent link to this record
 
 
Author German Barquero; Sergio Escalera; Cristina Palmero
Title Seamless Human Motion Composition with Blended Positional Encodings Type Miscellaneous
Year 2024 Publication Arxiv Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Conditional human motion generation is an important topic with many applications in virtual reality, gaming, and robotics. While prior works have focused on generating motion guided by text, music, or scenes, these typically result in isolated motions confined to short durations. Instead, we address the generation of long, continuous sequences guided by a series of varying textual descriptions. In this context, we introduce FlowMDM, the first diffusion-based model that generates seamless Human Motion Compositions (HMC) without any postprocessing or redundant denoising steps. For this, we introduce the Blended Positional Encodings, a technique that leverages both absolute and relative positional encodings in the denoising chain. More specifically, global motion coherence is recovered at the absolute stage, whereas smooth and realistic transitions are built at the relative stage. As a result, we achieve state-of-the-art results in terms of accuracy, realism, and smoothness on the Babel and HumanML3D datasets. FlowMDM excels when trained with only a single description per motion sequence thanks to its Pose-Centric Cross-ATtention, which makes it robust against varying text descriptions at inference time. Finally, to address the limitations of existing HMC metrics, we propose two new metrics: the Peak Jerk and the Area Under the Jerk, to detect abrupt transitions.
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 @ BEP2024 Serial 4022
Permanent link to this record
 
 
Author Alex Gomez-Villa; Bartlomiej Twardowski; Kai Wang; Joost van de Weijer
Title Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning Type Conference Article
Year 2024 Publication Winter Conference on Applications of Computer Vision Abbreviated Journal
Volume Issue Pages 1690-1700
Keywords
Abstract (up) Continuous unsupervised representation learning (CURL) research has greatly benefited from improvements in self-supervised learning (SSL) techniques. As a result, existing CURL methods using SSL can learn high-quality representations without any labels, but with a notable performance drop when learning on a many-tasks data stream. We hypothesize that this is caused by the regularization losses that are imposed to prevent forgetting, leading to a suboptimal plasticity-stability trade-off: they either do not adapt fully to the incoming data (low plasticity), or incur significant forgetting when allowed to fully adapt to a new SSL pretext-task (low stability). In this work, we propose to train an expert network that is relieved of the duty of keeping the previous knowledge and can focus on performing optimally on the new tasks (optimizing plasticity). In the second phase, we combine this new knowledge with the previous network in an adaptation-retrospection phase to avoid forgetting and initialize a new expert with the knowledge of the old network. We perform several experiments showing that our proposed approach outperforms other CURL exemplar-free methods in few- and many-task split settings. Furthermore, we show how to adapt our approach to semi-supervised continual learning (Semi-SCL) and show that we surpass the accuracy of other exemplar-free Semi-SCL methods and reach the results of some others that use exemplars.
Address Waikoloa; Hawai; USA; January 2024
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 WACV
Notes LAMP Approved no
Call Number Admin @ si @ GTW2024 Serial 3989
Permanent link to this record
 
 
Author Ayan Banerjee; Sanket Biswas; Josep Llados; Umapada Pal
Title SemiDocSeg: Harnessing Semi-Supervised Learning for Document Layout Analysis Type Journal Article
Year 2024 Publication International Journal on Document Analysis and Recognition Abbreviated Journal IJDAR
Volume Issue Pages
Keywords Document layout analysis; Semi-supervised learning; Co-Occurrence matrix; Instance segmentation; Swin transformer
Abstract (up) Document Layout Analysis (DLA) is the process of automatically identifying and categorizing the structural components (e.g. Text, Figure, Table, etc.) within a document to extract meaningful content and establish the page's layout structure. It is a crucial stage in document parsing, contributing to their comprehension. However, traditional DLA approaches often demand a significant volume of labeled training data, and the labor-intensive task of generating high-quality annotated training data poses a substantial challenge. In order to address this challenge, we proposed a semi-supervised setting that aims to perform learning on limited annotated categories by eliminating exhaustive and expensive mask annotations. The proposed setting is expected to be generalizable to novel categories as it learns the underlying positional information through a support set and class information through Co-Occurrence that can be generalized from annotated categories to novel categories. Here, we first extract features from the input image and support set with a shared multi-scale feature acquisition backbone. Then, the extracted feature representation is fed to the transformer encoder as a query. Later on, we utilize a semantic embedding network before the decoder to capture the underlying semantic relationships and similarities between different instances, enabling the model to make accurate predictions or classifications with only a limited amount of labeled data. Extensive experimentation on competitive benchmarks like PRIMA, DocLayNet, and Historical Japanese (HJ) demonstrate that this generalized setup obtains significant performance compared to the conventional supervised approach.
Address June 2024
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 @ BBL2024a Serial 4001
Permanent link to this record
 
 
Author Hao Fang; Ajian Liu; Jun Wan; Sergio Escalera; Chenxu Zhao; Xu Zhang; Stan Z Li; Zhen Lei
Title Surveillance Face Anti-spoofing Type Journal Article
Year 2024 Publication IEEE Transactions on Information Forensics and Security Abbreviated Journal TIFS
Volume 19 Issue Pages 1535-1546
Keywords
Abstract (up) Face Anti-spoofing (FAS) is essential to secure face recognition systems from various physical attacks. However, recent research generally focuses on short-distance applications (i.e., phone unlocking) while lacking consideration of long-distance scenes (i.e., surveillance security checks). In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks. In this scene, low image resolution and noise interference are new challenges faced in surveillance FAS. Together with the SuHiFiMask dataset, we propose a Contrastive Quality-Invariance Learning (CQIL) network to alleviate the performance degradation caused by image quality from three aspects: (1) An Image Quality Variable module (IQV) is introduced to recover image information associated with discrimination by combining the super-resolution network. (2) Using generated sample pairs to simulate quality variance distributions to help contrastive learning strategies obtain robust feature representation under quality variation. (3) A Separate Quality Network (SQN) is designed to learn discriminative features independent of image quality. Finally, a large number of experiments verify the quality of the SuHiFiMask dataset and the superiority of the proposed CQIL.
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 @ FLW2024 Serial 3869
Permanent link to this record
 
 
Author Hector Laria Mantecon; Kai Wang; Joost Van de Weijer; Bogdan Raducanu; Kai Wang
Title NeRF-Diffusion for 3D-Consistent Face Generation and Editing Type Conference Article
Year 2024 Publication 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Generating high-fidelity 3D-aware images without 3D supervision is a valuable capability in various applications. Current methods based on NeRF features, SDF information, or triplane features have limited variation after training. To address this, we propose a novel approach that combines pretrained models for shape and content generation. Our method leverages a pretrained Neural Radiance Field as a shape prior and a diffusion model for content generation. By conditioning the diffusion model with 3D features, we enhance its ability to generate novel views with 3D awareness. We introduce a consistency token shared between the NeRF module and the diffusion model to maintain 3D consistency during sampling. Moreover, our framework allows for text editing of 3D-aware image generation, enabling users to modify the style over 3D views while preserving semantic content. Our contributions include incorporating 3D awareness into a text-to-image model, addressing identity consistency in 3D view synthesis, and enabling text editing of 3D-aware image generation. We provide detailed explanations, including the shape prior based on the NeRF model and the content generation process using the diffusion model. We also discuss challenges such as shape consistency and sampling saturation. Experimental results demonstrate the effectiveness and visual quality of our approach.
Address Roma; Italia; February 2024
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 VISAPP
Notes LAMP Approved no
Call Number Admin @ si @ LWW2024 Serial 4003
Permanent link to this record
 
 
Author Yaxing Wang; Abel Gonzalez-Garcia; Chenshen Wu; Luis Herranz; Fahad Shahbaz Khan; Shangling Jui; Jian Yang; Joost Van de Weijer
Title MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains Type Journal Article
Year 2024 Publication International Journal of Computer Vision Abbreviated Journal IJCV
Volume 132 Issue Pages 490–514
Keywords
Abstract (up) Given the often enormous effort required to train GANs, both computationally as well as in dataset collection, the re-use of pretrained GANs largely increases the potential impact of generative models. Therefore, we propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs. This is done using a miner network that identifies which part of the generative distribution of each pretrained GAN outputs samples closest to the target domain. Mining effectively steers GAN sampling towards suitable regions of the latent space, which facilitates the posterior finetuning and avoids pathologies of other methods, such as mode collapse and lack of flexibility. Furthermore, to prevent overfitting on small target domains, we introduce sparse subnetwork selection, that restricts the set of trainable neurons to those that are relevant for the target dataset. We perform comprehensive experiments on several challenging datasets using various GAN architectures (BigGAN, Progressive GAN, and StyleGAN) and show that the proposed method, called MineGAN, effectively transfers knowledge to domains with few target images, outperforming existing methods. In addition, MineGAN can successfully transfer knowledge from multiple pretrained GANs. MineGAN.
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 @ WGW2024 Serial 3888
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 (up) 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 Patricia Suarez; Dario Carpio; Angel Sappa
Title Enhancement of guided thermal image super-resolution approaches Type Journal Article
Year 2024 Publication Neurocomputing Abbreviated Journal NEUCOM
Volume 573 Issue 127197 Pages 1-17
Keywords
Abstract (up) Guided image processing techniques are widely used to extract meaningful information from a guiding image and facilitate the enhancement of the guided one. This paper specifically addresses the challenge of guided thermal image super-resolution, where a low-resolution thermal image is enhanced using a high-resolution visible spectrum image. We propose a new strategy that enhances outcomes from current guided super-resolution methods. This is achieved by transforming the initial guiding data into a representation resembling a thermal-like image, which is more closely in sync with the intended output. Experimental results with upscale factors of 8 and 16, demonstrate the outstanding performance of our approach in guided thermal image super-resolution obtained by mapping the original guiding information to a thermal-like image representation.
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 MSIAU Approved no
Call Number Admin @ si @ SCS2024 Serial 3998
Permanent link to this record
 
 
Author Aura Hernandez-Sabate; Jose Elias Yauri; Pau Folch; Daniel Alvarez; Debora Gil
Title EEG Dataset Collection for Mental Workload Predictions in Flight-Deck Environment Type Journal Article
Year 2024 Publication Sensors Abbreviated Journal SENS
Volume 24 Issue 4 Pages 1174
Keywords
Abstract (up) High mental workload reduces human performance and the ability to correctly carry out complex tasks. In particular, aircraft pilots enduring high mental workloads are at high risk of failure, even with catastrophic outcomes. Despite progress, there is still a lack of knowledge about the interrelationship between mental workload and brain functionality, and there is still limited data on flight-deck scenarios. Although recent emerging deep-learning (DL) methods using physiological data have presented new ways to find new physiological markers to detect and assess cognitive states, they demand large amounts of properly annotated datasets to achieve good performance. We present a new dataset of electroencephalogram (EEG) recordings specifically collected for the recognition of different levels of mental workload. The data were recorded from three experiments, where participants were induced to different levels of workload through tasks of increasing cognition demand. The first involved playing the N-back test, which combines memory recall with arithmetical skills. The second was playing Heat-the-Chair, a serious game specifically designed to emphasize and monitor subjects under controlled concurrent tasks. The third was flying in an Airbus320 simulator and solving several critical situations. The design of the dataset has been validated on three different levels: (1) correlation of the theoretical difficulty of each scenario to the self-perceived difficulty and performance of subjects; (2) significant difference in EEG temporal patterns across the theoretical difficulties and (3) usefulness for the training and evaluation of AI models.
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 @ HYF2024 Serial 4019
Permanent link to this record
 
 
Author Beata Megyesi; Alicia Fornes; Nils Kopal; Benedek Lang
Title Historical Cryptology Type Book Chapter
Year 2024 Publication Learning and Experiencing Cryptography with CrypTool and SageMath Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Historical cryptology studies (original) encrypted manuscripts, often handwritten sources, produced in our history. These historical sources can be found in archives, often hidden without any indexing and therefore hard to locate. Once found they need to be digitized and turned into a machine-readable text format before they can be deciphered with computational methods. The focus of historical cryptology is not primarily the development of sophisticated algorithms for decipherment, but rather the entire process of analysis of the encrypted source from collection and digitization to transcription and decryption. The process also includes the interpretation and contextualization of the message set in its historical context. There are many challenges on the way, such as mistakes made by the scribe, errors made by the transcriber, damaged pages, handwriting styles that are difficult to interpret, historical languages from various time periods, and hidden underlying language of the message. Ciphertexts vary greatly in terms of their code system and symbol sets used with more or less distinguishable symbols. Ciphertexts can be embedded in clearly written text, or shorter or longer sequences of cleartext can be embedded in the ciphertext. The ciphers used mostly in historical times are substitutions (simple, homophonic, or polyphonic), with or without nomenclatures, encoded as digits or symbol sequences, with or without spaces. So the circumstances are different from those in modern cryptography which focuses on methods (algorithms) and their strengths and assumes that the algorithm is applied correctly. For both historical and modern cryptology, attack vectors outside the algorithm are applied like implementation flaws and side-channel attacks. In this chapter, we give an introduction to the field of historical cryptology and present an overview of how researchers today process historical encrypted sources.
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 @ MFK2024 Serial 4020
Permanent link to this record
 
 
Author Javier Vazquez; Graham D. Finlayson; Luis Herranz
Title Improving the perception of low-light enhanced images Type Journal Article
Year 2024 Publication Optics Express Abbreviated Journal
Volume 32 Issue 4 Pages 5174-5190
Keywords
Abstract (up) Improving images captured under low-light conditions has become an important topic in computational color imaging, as it has a wide range of applications. Most current methods are either based on handcrafted features or on end-to-end training of deep neural networks that mostly focus on minimizing some distortion metric —such as PSNR or SSIM— on a set of training images. However, the minimization of distortion metrics does not mean that the results are optimal in terms of perception (i.e. perceptual quality). As an example, the perception-distortion trade-off states that, close to the optimal results, improving distortion results in worsening perception. This means that current low-light image enhancement methods —that focus on distortion minimization— cannot be optimal in the sense of obtaining a good image in terms of perception errors. In this paper, we propose a post-processing approach in which, given the original low-light image and the result of a specific method, we are able to obtain a result that resembles as much as possible that of the original method, but, at the same time, giving an improvement in the perception of the final image. More in detail, our method follows the hypothesis that in order to minimally modify the perception of an input image, any modification should be a combination of a local change in the shading across a scene and a global change in illumination color. We demonstrate the ability of our method quantitatively using perceptual blind image metrics such as BRISQUE, NIQE, or UNIQUE, and through user preference tests.
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 MACO Approved no
Call Number Admin @ si @ VFH2024 Serial 4018
Permanent link to this record
 
 
Author Tao Wu; Kai Wang; Chuanming Tang; Jianlin Zhang
Title Diffusion-based network for unsupervised landmark detection Type Journal Article
Year 2024 Publication Knowledge-Based Systems Abbreviated Journal
Volume 292 Issue Pages 111627
Keywords
Abstract (up) Landmark detection is a fundamental task aiming at identifying specific landmarks that serve as representations of distinct object features within an image. However, the present landmark detection algorithms often adopt complex architectures and are trained in a supervised manner using large datasets to achieve satisfactory performance. When faced with limited data, these algorithms tend to experience a notable decline in accuracy. To address these drawbacks, we propose a novel diffusion-based network (DBN) for unsupervised landmark detection, which leverages the generation ability of the diffusion models to detect the landmark locations. In particular, we introduce a dual-branch encoder (DualE) for extracting visual features and predicting landmarks. Additionally, we lighten the decoder structure for faster inference, referred to as LightD. By this means, we avoid relying on extensive data comparison and the necessity of designing complex architectures as in previous methods. Experiments on CelebA, AFLW, 300W and Deepfashion benchmarks have shown that DBN performs state-of-the-art compared to the existing methods. Furthermore, DBN shows robustness even when faced with limited data cases.
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 @ WWT2024 Serial 4024
Permanent link to this record
 
 
Author Ayan Banerjee; Sanket Biswas; Josep Llados; Umapada Pal
Title GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation Type Miscellaneous
Year 2024 Publication Arxiv Abbreviated Journal
Volume Issue Pages
Keywords
Abstract (up) Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements. Large and complex models, while achieving high accuracy, can be computationally expensive and memory-intensive, making them impractical for deployment on resource constrained devices. Knowledge distillation allows us to create small and more efficient models that retain much of the performance of their larger counterparts. Here we present a graph-based knowledge distillation framework to correctly identify and localize the document objects in a document image. Here, we design a structured graph with nodes containing proposal-level features and edges representing the relationship between the different proposal regions. Also, to reduce text bias an adaptive node sampling strategy is designed to prune the weight distribution and put more weightage on non-text nodes. We encode the complete graph as a knowledge representation and transfer it from the teacher to the student through the proposed distillation loss by effectively capturing both local and global information concurrently. Extensive experimentation on competitive benchmarks demonstrates that the proposed framework outperforms the current state-of-the-art approaches. The code will be available at: this https URL.
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 @ BBL2024b Serial 4023
Permanent link to this record