... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision最新文献

{"title":"Self-Supervised Anomaly Detection from Anomalous Training Data via Iterative Latent Token Masking.","authors":"Ashay Patel, Petru-Daniel Tudosiu, Walter H L Pinaya, Mark S Graham, Olusola Adeleke, Gary Cook, Vicky Goh, Sebastien Ourselin, M Jorge Cardoso","doi":"10.1109/ICCVW60793.2023.00254","DOIUrl":"10.1109/ICCVW60793.2023.00254","url":null,"abstract":"<p><p>Anomaly detection and segmentation pose an important task across sectors ranging from medical imaging analysis to industry quality control. However, current unsupervised approaches require training data to not contain any anomalies, a requirement that can be especially challenging in many medical imaging scenarios. In this paper, we propose Iterative Latent Token Masking, a self-supervised framework derived from a robust statistics point of view, translating an iterative model fitting with M-estimators to the task of anomaly detection. In doing so, this allows the training of unsupervised methods on datasets heavily contaminated with anomalous images. Our method stems from prior work on using Transformers, combined with a Vector Quantized-Variational Autoencoder, for anomaly detection, a method with state-of-the-art performance when trained on normal (non-anomalous) data. More importantly, we utilise the token masking capabilities of Transformers to filter out suspected anomalous tokens from each sample's sequence in the training set in an iterative self-supervised process, thus overcoming the difficulties of highly anomalous training data. Our work also highlights shortfalls in current state-of-the-art self-supervised, self-trained and unsupervised models when faced with small proportions of anomalous training data. We evaluate our method on whole-body PET data in addition to showing its wider application in more common computer vision tasks such as the industrial MVTec Dataset. Using varying levels of anomalous training data, our method showcases a superior performance over several state-of-the-art models, drawing attention to the potential of this approach.</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":"2023 ","pages":"2394-2402"},"PeriodicalIF":0.0,"publicationDate":"2023-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7616405/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142115474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"STRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Prediction.","authors":"Cristina González, Nicolás Ayobi, Felipe Escallón, Laura Baldovino-Chiquillo, Maria Wilches-Mogollón, Donny Pasos, Nicole Ramírez, Jose Pinzón, Olga Sarmiento, D Alex Quistberg, Pablo Arbeláez","doi":"10.1109/iccvw60793.2023.00347","DOIUrl":"10.1109/iccvw60793.2023.00347","url":null,"abstract":"<p><p>This paper introduces a novel benchmark to study the impact and relationship of built environment elements on pedestrian collision prediction, intending to enhance environmental awareness in autonomous driving systems to prevent pedestrian injuries actively. We introduce a built environment detection task in large-scale panoramic images and a detection-based pedestrian collision frequency prediction task. We propose a baseline method that incorporates a collision prediction module into a state-of-the-art detection model to tackle both tasks simultaneously. Our experiments demonstrate a significant correlation between object detection of built environment elements and pedestrian collision frequency prediction. Our results are a stepping stone towards understanding the interdependencies between built environment conditions and pedestrian safety.</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":"2023 ","pages":"3222-3234"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11298792/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141894982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning to Learn: How to Continuously Teach Humans and Machines.","authors":"Parantak Singh, You Li, Ankur Sikarwar, Weixian Lei, Difei Gao, Morgan B Talbot, Ying Sun, Mike Zheng Shou, Gabriel Kreiman, Mengmi Zhang","doi":"10.1109/iccv51070.2023.01075","DOIUrl":"10.1109/iccv51070.2023.01075","url":null,"abstract":"<p><p>Curriculum design is a fundamental component of education. For example, when we learn mathematics at school, we build upon our knowledge of addition to learn multiplication. These and other concepts must be mastered before our first algebra lesson, which also reinforces our addition and multiplication skills. Designing a curriculum for teaching either a human or a machine shares the underlying goal of maximizing knowledge transfer from earlier to later tasks, while also minimizing forgetting of learned tasks. Prior research on curriculum design for image classification focuses on the ordering of training examples during a single offline task. Here, we investigate the effect of the order in which multiple distinct tasks are learned in a sequence. We focus on the online class-incremental continual learning setting, where algorithms or humans must learn image classes one at a time during a single pass through a dataset. We find that curriculum consistently influences learning outcomes for humans and for multiple continual machine learning algorithms across several benchmark datasets. We introduce a novel-object recognition dataset for human curriculum learning experiments and observe that curricula that are effective for humans are highly correlated with those that are effective for machines. As an initial step towards automated curriculum design for online class-incremental learning, we propose a novel algorithm, dubbed Curriculum Designer (CD), that designs and ranks curricula based on inter-class feature similarities. We find significant overlap between curricula that are empirically highly effective and those that are highly ranked by our CD. Our study establishes a framework for further research on teaching humans and machines to learn continuously using optimized curricula. Our code and data are available through this link.</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":"2023 ","pages":"11674-11685"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11114607/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141089330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-supervised Semantic Segmentation: Consistency over Transformation.","authors":"Sanaz Karimijafarbigloo, Reza Azad, Amirhossein Kazerouni, Yury Velichko, Ulas Bagci, Dorit Merhof","doi":"10.1109/ICCVW60793.2023.00280","DOIUrl":"10.1109/ICCVW60793.2023.00280","url":null,"abstract":"<p><p>Accurate medical image segmentation is of utmost importance for enabling automated clinical decision procedures. However, prevailing supervised deep learning approaches for medical image segmentation encounter significant challenges due to their heavy dependence on extensive labeled training data. To tackle this issue, we propose a novel self-supervised algorithm, <math><mrow><mrow><msup><mi>S</mi><mn>3</mn></msup></mrow><mo>-</mo><mi>Net</mi></mrow></math>, which integrates a robust framework based on the proposed Inception Large Kernel Attention (I-LKA) modules. This architectural enhancement makes it possible to comprehensively capture contextual information while preserving local intricacies, thereby enabling precise semantic segmentation. Furthermore, considering that lesions in medical images often exhibit deformations, we leverage deformable convolution as an integral component to effectively capture and delineate lesion deformations for superior object boundary definition. Additionally, our self-supervised strategy emphasizes the acquisition of invariance to affine transformations, which is commonly encountered in medical scenarios. This emphasis on robustness with respect to geometric distortions significantly enhances the model's ability to accurately model and handle such distortions. To enforce spatial consistency and promote the grouping of spatially connected image pixels with similar feature representations, we introduce a spatial consistency loss term. This aids the network in effectively capturing the relationships among neighboring pixels and enhancing the overall segmentation quality. The <math><mrow><mrow><msup><mi>S</mi><mn>3</mn></msup></mrow><mo>-</mo><mi>N</mi><mi>e</mi><mi>t</mi></mrow></math> approach iteratively learns pixel-level feature representations for image content clustering in an end-to-end manner. Our experimental results on skin lesion and lung organ segmentation tasks show the superior performance of our method compared to the SOTA approaches.</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":"2023 ","pages":"2646-2655"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10829429/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139652364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust AMD Stage Grading with Exclusively OCTA Modality Leveraging 3D Volume.","authors":"Haochen Zhang, Anna Heinke, Carlo Miguel B Galang, Daniel N Deussen, Bo Wen, Dirk-Uwe G Bartsch, William R Freeman, Truong Q Nguyen, Cheolhong An","doi":"10.1109/ICCVW60793.2023.00255","DOIUrl":"10.1109/ICCVW60793.2023.00255","url":null,"abstract":"<p><p>Age-related Macular Degeneration (AMD) is a degenerative eye disease that causes central vision loss. Optical Coherence Tomography Angiography (OCTA) is an emerging imaging modality that aids in the diagnosis of AMD by displaying the pathogenic vessels in the subretinal space. In this paper, we investigate the effectiveness of OCTA from the view of deep classifiers. To the best of our knowledge, this is the first study that solely uses OCTA for AMD stage grading. By developing a 2D classifier based on OCTA projections, we identify that segmentation errors in retinal layers significantly affect the accuracy of classification. To address this issue, we propose analyzing 3D OCTA volumes directly using a 2D convolutional neural network trained with additional projection supervision. Our experimental results show that we achieve over 80% accuracy on a four-stage grading task on both error-free and error-prone test sets, which is significantly higher than 60%, the accuracy of human experts. This demonstrates that OCTA provides sufficient information for AMD stage grading and the proposed 3D volume analyzer is more robust when dealing with OCTA data with segmentation errors.</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":"2023 ","pages":"2403-2412"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11340655/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142037878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes.","authors":"Philipp Bomatter, Mengmi Zhang, Dimitar Karev, Spandan Madan, Claire Tseng, Gabriel Kreiman","doi":"10.1109/iccv48922.2021.00032","DOIUrl":"10.1109/iccv48922.2021.00032","url":null,"abstract":"<p><p>Context is of fundamental importance to both human and machine vision; e.g., an object in the air is more likely to be an airplane than a pig. The rich notion of context incorporates several aspects including physics rules, statistical co-occurrences, and relative object sizes, among others. While previous work has focused on crowd-sourced out-of-context photographs from the web to study scene context, controlling the nature and extent of contextual violations has been a daunting task. Here we introduce a diverse, synthetic <b>O</b>ut-of-<b>C</b>ontext <b>D</b>ataset (OCD) with fine-grained control over scene context. By leveraging a 3D simulation engine, we systematically control the gravity, object co-occurrences and relative sizes across 36 object categories in a virtual household environment. We conducted a series of experiments to gain insights into the impact of contextual cues on both human and machine vision using OCD. We conducted psychophysics experiments to establish a human benchmark for out-of-context recognition, and then compared it with state-of-the-art computer vision models to quantify the gap between the two. We propose a context-aware recognition transformer model, fusing object and contextual information via multi-head attention. Our model captures useful information for contextual reasoning, enabling human-level performance and better robustness in out-of-context conditions compared to baseline models across OCD and other out-of-context datasets. All source code and data are publicly available at https://github.com/kreimanlab/WhenPigsFlyContext.</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":" ","pages":"255-264"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9432425/pdf/nihms-1831598.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"40342711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-scanner Harmonization of Paired Neuroimaging Data via Structure Preserving Embedding Learning.","authors":"Mahbaneh Eshaghzadeh Torbati, Dana L Tudorascu, Davneet S Minhas, Pauline Maillard, Charles S DeCarli, Seong Jae Hwang","doi":"10.1109/ICCVW54120.2021.00367","DOIUrl":"10.1109/ICCVW54120.2021.00367","url":null,"abstract":"<p><p>Combining datasets from multiple sites/scanners has been becoming increasingly more prevalent in modern neuroimaging studies. Despite numerous benefits from the growth in sample size, substantial technical variability associated with site/scanner-related effects exists which may inadvertently bias subsequent downstream analyses. Such a challenge calls for a data harmonization procedure which reduces the scanner effects and allows the scans to be combined for pooled analyses. In this work, we present MISPEL (Multi-scanner Image harmonization via Structure Preserving Embedding Learning), a multi-scanner harmonization framework. Unlike existing techniques, MISPEL does not assume a perfect coregistration across the scans, and the framework is naturally extendable to more than two scanners. Importantly, we incorporate our multi-scanner dataset where each subject is scanned on four different scanners. This unique paired dataset allows us to define and aim for an ideal harmonization (e.g., each subject with identical brain tissue volumes on all scanners). We extensively view scanner effects under varying metrics and demonstrate how MISPEL significantly improves them.</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":" ","pages":"3277-3286"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8668020/pdf/nihms-1760021.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39728309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint Semi-supervised and Active Learning for Segmentation of Gigapixel Pathology Images with Cost-Effective Labeling.","authors":"Zhengfeng Lai,&nbsp;Chao Wang,&nbsp;Luca Cerny Oliveira,&nbsp;Brittany N Dugger,&nbsp;Sen-Ching Cheung,&nbsp;Chen-Nee Chuah","doi":"10.1109/iccvw54120.2021.00072","DOIUrl":"https://doi.org/10.1109/iccvw54120.2021.00072","url":null,"abstract":"<p><p>The need for manual and detailed annotations limits the applicability of supervised deep learning algorithms in medical image analyses, specifically in the field of pathology. Semi-supervised learning (SSL) provides an effective way for leveraging unlabeled data to relieve the heavy reliance on the amount of labeled samples when training a model. Although SSL has shown good performance, the performance of recent state-of-the-art SSL methods on pathology images is still under study. The problem for selecting the most optimal data to label for SSL is not fully explored. To tackle this challenge, we propose a semi-supervised active learning framework with a region-based selection criterion. This framework iteratively selects regions for annotation query to quickly expand the diversity and volume of the labeled set. We evaluate our framework on a grey-matter/white-matter segmentation problem using gigapixel pathology images from autopsied human brain tissues. With only 0.1% regions labeled, our proposed algorithm can reach a competitive IoU score compared to fully-supervised learning and outperform the current state-of-the-art SSL by more than 10% of IoU score and DICE coefficient.</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":"2021 ","pages":"591-600"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8972970/pdf/nihms-1788370.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10656111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decision Explanation and Feature Importance for Invertible Networks.","authors":"Juntang Zhuang,&nbsp;Nicha C Dvornek,&nbsp;Xiaoxiao Li,&nbsp;Junlin Yang,&nbsp;James S Duncan","doi":"10.1109/iccvw.2019.00521","DOIUrl":"https://doi.org/10.1109/iccvw.2019.00521","url":null,"abstract":"<p><p>Deep neural networks are vulnerable to adversarial attacks and hard to interpret because of their black-box nature. The recently proposed invertible network is able to accurately reconstruct the inputs to a layer from its outputs, thus has the potential to unravel the black-box model. An invertible network classifier can be viewed as a two-stage model: (1) invertible transformation from input space to the feature space; (2) a linear classifier in the feature space. We can determine the decision boundary of a linear classifier in the feature space; since the transform is invertible, we can invert the decision boundary from the feature space to the input space. Furthermore, we propose to determine the projection of a data point onto the decision boundary, and define explanation as the difference between data and its projection. Finally, we propose to locally approximate a neural network with its first-order Taylor expansion, and define feature importance using a local linear model. We provide the implementation of our method: https://github.com/juntang-zhuang/explain_invertible.</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":"2019 ","pages":"4235-4239"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/iccvw.2019.00521","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38462061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation.","authors":"Junlin Yang, Nicha C Dvornek, Fan Zhang, Juntang Zhuang, Julius Chapiro, MingDe Lin, James S Duncan","doi":"10.1109/iccvw.2019.00043","DOIUrl":"10.1109/iccvw.2019.00043","url":null,"abstract":"<p><p>Domain Adaptation (DA) has the potential to greatly help the generalization of deep learning models. However, the current literature usually assumes to transfer the knowledge from the source domain to a specific known target domain. Domain Agnostic Learning (DAL) proposes a new task of transferring knowledge from the source domain to data from multiple heterogeneous target domains. In this work, we propose the Domain-Agnostic Learning framework with Anatomy-Consistent Embedding (DALACE) that works on both domain-transfer and task-transfer to learn a disentangled representation, aiming to not only be invariant to different modalities but also preserve anatomical structures for the DA and DAL tasks in cross-modality liver segmentation. We validated and compared our model with state-of-the-art methods, including CycleGAN, Task Driven Generative Adversarial Network (TD-GAN), and Domain Adaptation via Disentangled Representations (DADR). For the DA task, our DALACE model outperformed CycleGAN, TD-GAN, and DADR with DSC of 0.847 compared to 0.721, 0.793 and 0.806. For the DAL task, our model improved the performance with DSC of 0.794 from 0.522, 0.719 and 0.742 by CycleGAN, TD-GAN, and DADR. Further, we visualized the success of disentanglement, which added human interpretability of the learned meaningful representations. Through ablation analysis, we specifically showed the concrete benefits of disentanglement for downstream tasks and the role of supervision for better disentangled representation with segmentation consistency to be invariant to domains with the proposed Domain-Agnostic Module (DAM) and to preserve anatomical information with the proposed Anatomy-Preserving Module (APM).</p>","PeriodicalId":72022,"journal":{"name":"... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision","volume":"2019 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8528125/pdf/nihms-1596812.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39539140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}