Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
Switching between tasks can cause AI to lose the ability to learn
The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities… (voir plus). Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing pre-trained self-supervised features. However, so far, object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the wider trend in machine learning towards general-purpose models directly applicable to unseen data and tasks. Thus, in this work, we study current object-centric methods through the lens of zero-shot generalization by introducing a benchmark comprising eight different synthetic and real-world datasets. We analyze the factors influencing zero-shot performance and find that training on diverse real-world images improves transferability to unseen scenarios. Furthermore, inspired by the success of task-specific fine-tuning in foundation models, we introduce a novel fine-tuning strategy to adapt pre-trained vision encoders for the task of object discovery. We find that the proposed approach results in state-of-the-art performance for unsupervised object discovery, exhibiting strong zero-shot transfer to unseen datasets.
The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities… (voir plus). Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing pre-trained self-supervised features. However, so far, object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the wider trend in machine learning towards general-purpose models directly applicable to unseen data and tasks. Thus, in this work, we study current object-centric methods through the lens of zero-shot generalization by introducing a benchmark comprising eight different synthetic and real-world datasets. We analyze the factors influencing zero-shot performance and find that training on diverse real-world images improves transferability to unseen scenarios. Furthermore, inspired by the success of task-specific fine-tuning in foundation models, we introduce a novel fine-tuning strategy to adapt pre-trained vision encoders for the task of object discovery. We find that the proposed approach results in state-of-the-art performance for unsupervised object discovery, exhibiting strong zero-shot transfer to unseen datasets.
The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities… (voir plus). Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing pre-trained self-supervised features. However, so far, object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the wider trend in machine learning towards general-purpose models directly applicable to unseen data and tasks. Thus, in this work, we study current object-centric methods through the lens of zero-shot generalization by introducing a benchmark comprising eight different synthetic and real-world datasets. We analyze the factors influencing zero-shot performance and find that training on diverse real-world images improves transferability to unseen scenarios. Furthermore, inspired by the success of task-specific fine-tuning in foundation models, we introduce a novel fine-tuning strategy to adapt pre-trained vision encoders for the task of object discovery. We find that the proposed approach results in state-of-the-art performance for unsupervised object discovery, exhibiting strong zero-shot transfer to unseen datasets.
Deep generative models learn continuous representations of complex data manifolds using a finite number of samples during training. For a pr… (voir plus)e-trained generative model, the common way to evaluate the quality of the manifold representation learned, is by computing global metrics like Fr\'echet Inception Distance using a large number of generated and real samples. However, generative model performance is not uniform across the learned manifold, e.g., for \textit{foundation models} like Stable Diffusion generation performance can vary significantly based on the conditioning or initial noise vector being denoised. In this paper we study the relationship between the \textit{local geometry of the learned manifold} and downstream generation. Based on the theory of continuous piecewise-linear (CPWL) generators, we use three geometric descriptors - scaling (
PURPOSE
Advancing the development of 7 T MRI for spinal cord imaging is crucial for the enhanced diagnosis and monitoring of various neurode… (voir plus)generative diseases and traumas. However, a significant challenge at this field strength is the transmit field inhomogeneity. Such inhomogeneity is particularly problematic for imaging the small, deep anatomical structures of the cervical spinal cord, as it can cause uneven signal intensity and elevate the local specific absorption ratio, compromising image quality. This multisite study explores several RF shimming techniques in the cervical spinal cord.
METHODS
Data were collected from 5 participants between two 7 T sites with a custom 8Tx/20Rx parallel transmission coil. We explored two radiofrequency (RF) shimming approaches from an MRI vendor and four from an open-source toolbox, showcasing their ability to enhance transmit field and signal homogeneity along the cervical spinal cord.
RESULTS
The circularly polarized (CP), coefficient of variation (CoV), and specific absorption rate (SAR) efficiency shim modes showed the highest B1 + efficiency, and the vendor-based "patient" and "volume" modes showed the lowest B1 + efficiency. The coefficient of variation method produced the highest CSF/spinal cord contrast on T2*-weighted scans (ratio of 1.27 ± 0.03), and the lowest variation of that contrast along the superior-inferior axis.
CONCLUSION
The study's findings highlight the potential of RF shimming to advance 7 T MRI's clinical utility for central nervous system imaging by enabling more homogenous and efficient spinal cord imaging. Additionally, the research incorporates a reproducible Jupyter Notebook, enhancing the study's transparency and facilitating peer verification.
PURPOSE
Advancing the development of 7 T MRI for spinal cord imaging is crucial for the enhanced diagnosis and monitoring of various neurode… (voir plus)generative diseases and traumas. However, a significant challenge at this field strength is the transmit field inhomogeneity. Such inhomogeneity is particularly problematic for imaging the small, deep anatomical structures of the cervical spinal cord, as it can cause uneven signal intensity and elevate the local specific absorption ratio, compromising image quality. This multisite study explores several RF shimming techniques in the cervical spinal cord.
METHODS
Data were collected from 5 participants between two 7 T sites with a custom 8Tx/20Rx parallel transmission coil. We explored two radiofrequency (RF) shimming approaches from an MRI vendor and four from an open-source toolbox, showcasing their ability to enhance transmit field and signal homogeneity along the cervical spinal cord.
RESULTS
The circularly polarized (CP), coefficient of variation (CoV), and specific absorption rate (SAR) efficiency shim modes showed the highest B1 + efficiency, and the vendor-based "patient" and "volume" modes showed the lowest B1 + efficiency. The coefficient of variation method produced the highest CSF/spinal cord contrast on T2*-weighted scans (ratio of 1.27 ± 0.03), and the lowest variation of that contrast along the superior-inferior axis.
CONCLUSION
The study's findings highlight the potential of RF shimming to advance 7 T MRI's clinical utility for central nervous system imaging by enabling more homogenous and efficient spinal cord imaging. Additionally, the research incorporates a reproducible Jupyter Notebook, enhancing the study's transparency and facilitating peer verification.
The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particula… (voir plus)r domain or task. Model MoErging methods aim to recycle expert models to create an aggregate system with improved performance or generalization. A key component of MoErging methods is the creation of a router that decides which expert model(s) to use for a particular input or application. The promise, effectiveness, and large design space of MoErging has spurred the development of many new methods over the past few years. This rapid pace of development has made it challenging to compare different MoErging methods, which are rarely compared to one another and are often validated in different experimental setups. To remedy such gaps, we present a comprehensive survey of MoErging methods that includes a novel taxonomy for cataloging key design choices and clarifying suitable applications for each method. Apart from surveying MoErging research, we inventory software tools and applications that make use of MoErging. We additionally discuss related fields of study such as model merging, multitask learning, and mixture-of-experts models. Taken as a whole, our survey provides a unified overview of existing MoErging methods and creates a solid foundation for future work in this burgeoning field.
The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particula… (voir plus)r domain or task. Model MoErging methods aim to recycle expert models to create an aggregate system with improved performance or generalization. A key component of MoErging methods is the creation of a router that decides which expert model(s) to use for a particular input or application. The promise, effectiveness, and large design space of MoErging has spurred the development of many new methods over the past few years. This rapid pace of development has made it challenging to compare different MoErging methods, which are rarely compared to one another and are often validated in different experimental setups. To remedy such gaps, we present a comprehensive survey of MoErging methods that includes a novel taxonomy for cataloging key design choices and clarifying suitable applications for each method. Apart from surveying MoErging research, we inventory software tools and applications that make use of MoErging. We additionally discuss related fields of study such as model merging, multitask learning, and mixture-of-experts models. Taken as a whole, our survey provides a unified overview of existing MoErging methods and creates a solid foundation for future work in this burgeoning field.
Deep learning for time-series anomaly detection (TSAD) has gained significant attention over the past decade. Despite the reported improveme… (voir plus)nts in several papers, the practical application of these models remains limited. Recent studies have cast doubt on these models, attributing their results to flawed evaluation techniques. However, the impact of initialization has largely been overlooked. This paper provides a critical analysis of the initialization effects on TSAD model performance. Our extensive experiments reveal that TSAD models are highly sensitive to hyperparameters such as window size, seed number, and normalization. This sensitivity often leads to significant variability in performance, which can be exploited to artificially inflate the reported efficacy of these models. We demonstrate that even minor changes in initialization parameters can result in performance variations that overshadow the claimed improvements from novel model architectures. Our findings highlight the need for rigorous evaluation protocols and transparent reporting of preprocessing steps to ensure the reliability and fairness of anomaly detection methods. This paper calls for a more cautious interpretation of TSAD advancements and encourages the development of more robust and transparent evaluation practices to advance the field and its practical applications.
Deep learning for time-series anomaly detection (TSAD) has gained significant attention over the past decade. Despite the reported improveme… (voir plus)nts in several papers, the practical application of these models remains limited. Recent studies have cast doubt on these models, attributing their results to flawed evaluation techniques. However, the impact of initialization has largely been overlooked. This paper provides a critical analysis of the initialization effects on TSAD model performance. Our extensive experiments reveal that TSAD models are highly sensitive to hyperparameters such as window size, seed number, and normalization. This sensitivity often leads to significant variability in performance, which can be exploited to artificially inflate the reported efficacy of these models. We demonstrate that even minor changes in initialization parameters can result in performance variations that overshadow the claimed improvements from novel model architectures. Our findings highlight the need for rigorous evaluation protocols and transparent reporting of preprocessing steps to ensure the reliability and fairness of anomaly detection methods. This paper calls for a more cautious interpretation of TSAD advancements and encourages the development of more robust and transparent evaluation practices to advance the field and its practical applications.
