Search

Given a finite group $G$ and a commutative ring $G$-spectrum $R$, we study the separable commutative algebras in the category of compact $R$-modules. We isolate three conditions on the geometric fixed points of $R$ which ensure that every separable commutative algebra is standard, i.e. arises from a finite $G$-set. In particular we show that all separable commutative algebras in the categories of compact objects in $G$-spectra and in derived $G$-Mackey functors are standard provided that $G$ is a $p$-group. In these categories we also show that for a general finite group $G$, we cannot expect all separable commutative algebras to be standard., Comment: 26 pages

Given a symmetric monoidal stable $\infty$-category $\mathcal{C}$ which is rigidly-compactly generated and a set of compact objects $\mathcal{K}$ of $\mathcal{C}$, one can form the subcategories of $\mathcal{K}$-complete and $\mathcal{K}$-local objects. The goal of this paper is to explain how to recover $\mathcal{C}$ from its $\mathcal{K}$-local and $\mathcal{K}$-complete subcategories while retaining the symmetric monoidal structure. Specializing to the case where $\mathcal{C}$ is the $\infty$-category of $G$-spectra for a finite group $G$, our result can be viewed as a symmetric monoidal variant of the isotropy separation decomposition, a version of which appeared previously in work of Krause., Comment: 40 pages; all comments welcome!

We prove that for any presentably symmetric monoidal $\infty$-category $\mathcal{V}$, the $\infty$-category $\mathbf{Mod}_\mathcal{V}(\mathbf{Pr}^{\mathrm{L}})^{\mathrm{dbl}}$ of dualizable presentable $\mathcal{V}$-modules and internal left adjoints between them is itself presentable. Along the way, we survey formal properties of these dualizable $\mathcal V$-modules. We pay close attention to the case of the $\infty$-category of spectra, where we survey the foundational properties of ``compact morphisms''., Comment: 80 pages; comments welcome!

We survey the theory of locally rigid and rigid symmetric monoidal $\infty$-categories over an arbitrary base $\mathcal{V}\in\mathrm{CAlg}(\mathbf{Pr}^\mathrm{L})$. Along the way, we introduce and study ``$\mathcal{V}$-atomic morphisms'', which are analogues of compact morphisms over an arbitrary base $\mathcal{V}$., Comment: 59 pages, comments welcome!

Left ventricular ejection fraction (LVEF) is the most important clinical parameter of cardiovascular function. The accuracy in estimating this parameter is highly dependent upon the precise segmentation of the left ventricle (LV) structure at the end diastole and systole phases. Therefore, it is crucial to develop robust algorithms for the precise segmentation of the heart structure during different phases. Methodology: In this work, an improved 3D UNet model is introduced to segment the myocardium and LV, while excluding papillary muscles, as per the recommendation of the Society for Cardiovascular Magnetic Resonance. For the practical testing of the proposed framework, a total of 8,400 cardiac MRI images were collected and analysed from the military hospital in Tunis (HMPIT), as well as the popular ACDC public dataset. As performance metrics, we used the Dice coefficient and the F1 score for validation/testing of the LV and the myocardium segmentation. Results: The data was split into 70%, 10%, and 20% for training, validation, and testing, respectively. It is worth noting that the proposed segmentation model was tested across three axis views: basal, medio basal and apical at two different cardiac phases: end diastole and end systole instances. The experimental results showed a Dice index of 0.965 and 0.945, and an F1 score of 0.801 and 0.799, at the end diastolic and systolic phases, respectively. Additionally, clinical evaluation outcomes revealed a significant difference in the LVEF and other clinical parameters when the papillary muscles were included or excluded.

Vision Language Models (VLMs) have demonstrated remarkable capabilities in various open-vocabulary tasks, yet their zero-shot performance lags behind task-specific finetuned models, particularly in complex tasks like Referring Expression Comprehension (REC). Fine-tuning usually requires 'white-box' access to the model's architecture and weights, which is not always feasible due to proprietary or privacy concerns. In this work, we propose LLM-wrapper, a method for 'black-box' adaptation of VLMs for the REC task using Large Language Models (LLMs). LLM-wrapper capitalizes on the reasoning abilities of LLMs, improved with a light fine-tuning, to select the most relevant bounding box matching the referring expression, from candidates generated by a zero-shot black-box VLM. Our approach offers several advantages: it enables the adaptation of closed-source models without needing access to their internal workings, it is versatile as it works with any VLM, it transfers to new VLMs, and it allows for the adaptation of an ensemble of VLMs. We evaluate LLM-wrapper on multiple datasets using different VLMs and LLMs, demonstrating significant performance improvements and highlighting the versatility of our method. While LLM-wrapper is not meant to directly compete with standard white-box fine-tuning, it offers a practical and effective alternative for black-box VLM adaptation. The code will be open-sourced., Comment: v1 at EVAL-FoMo workshop, ECCV 2024

Field-aware Factorization Machines (FFMs) have emerged as a powerful model for click-through rate prediction, particularly excelling in capturing complex feature interactions. In this work, we present an in-depth analysis of our in-house, Rust-based Deep FFM implementation, and detail its deployment on a CPU-only, multi-data-center scale. We overview key optimizations devised for both training and inference, demonstrated by previously unpublished benchmark results in efficient model search and online training. Further, we detail an in-house weight quantization that resulted in more than an order of magnitude reduction in bandwidth footprint related to weight transfers across data-centres. We disclose the engine and associated techniques under an open-source license to contribute to the broader machine learning community. This paper showcases one of the first successful CPU-only deployments of Deep FFMs at such scale, marking a significant stride in practical, low-footprint click-through rate prediction methodologies., Comment: 6p, KDD2024 - AdKDD workshop

Graph Neural Networks (GNNs), especially message-passing-based models, have become prominent in top-k recommendation tasks, outperforming matrix factorization models due to their ability to efficiently aggregate information from a broader context. Although GNNs are evaluated with ranking-based metrics, e.g NDCG@k and Recall@k, they remain largely trained with proxy losses, e.g the BPR loss. In this work we explore the use of ranking loss functions to directly optimize the evaluation metrics, an area not extensively investigated in the GNN community for collaborative filtering. We take advantage of smooth approximations of the rank to facilitate end-to-end training of GNNs and propose a Personalized PageRank-based negative sampling strategy tailored for ranking loss functions. Moreover, we extend the evaluation of GNN models for top-k recommendation tasks with an inductive user-centric protocol, providing a more accurate reflection of real-world applications. Our proposed method significantly outperforms the standard BPR loss and more advanced losses across four datasets and four recent GNN architectures while also exhibiting faster training. Demonstrating the potential of ranking loss functions in improving GNN training for collaborative filtering tasks.

Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs), e.g. CLIP, for few-shot image classification. Despite their success, most prompt learning methods trade-off between classification accuracy and robustness, e.g. in domain generalization or out-of-distribution (OOD) detection. In this work, we introduce Global-Local Prompts (GalLoP), a new prompt learning method that learns multiple diverse prompts leveraging both global and local visual features. The training of the local prompts relies on local features with an enhanced vision-text alignment. To focus only on pertinent features, this local alignment is coupled with a sparsity strategy in the selection of the local features. We enforce diversity on the set of prompts using a new ``prompt dropout'' technique and a multiscale strategy on the local prompts. GalLoP outperforms previous prompt learning methods on accuracy on eleven datasets in different few shots settings and with various backbones. Furthermore, GalLoP shows strong robustness performances in both domain generalization and OOD detection, even outperforming dedicated OOD detection methods. Code and instructions to reproduce our results: https://github.com/MarcLafon/gallop.

Flow estimation problems are ubiquitous in scientific imaging. Often, the underlying flows are subject to physical constraints that can be exploited in the flow estimation; for example, incompressible (divergence-free) flows are expected for many fluid experiments, while irrotational (curl-free) flows arise in the analysis of optical distortions and wavefront sensing. In this work, we propose a Physics- Inspired Neural Network (PINN) named HDNet, which performs a Helmholtz decomposition of an arbitrary flow field, i.e., it decomposes the input flow into a divergence-only and a curl-only component. HDNet can be trained exclusively on synthetic data generated by reverse Helmholtz decomposition, which we call Helmholtz synthesis. As a PINN, HDNet is fully differentiable and can easily be integrated into arbitrary flow estimation problems.

With the ever-growing power of generative artificial intelligence, deepfake and artificially generated (synthetic) media have continued to spread online, which creates various ethical and moral concerns regarding their usage. To tackle this, we thus present a novel exploration of the trends and patterns observed in real, deepfake and synthetic facial images. The proposed analysis is done in two parts: firstly, we incorporate eight deep learning models and analyze their performances in distinguishing between the three classes of images. Next, we look to further delve into the similarities and differences between these three sets of images by investigating their image properties both in the context of the entire image as well as in the context of specific regions within the image. ANOVA test was also performed and provided further clarity amongst the patterns associated between the images of the three classes. From our findings, we observe that the investigated deeplearning models found it easier to detect synthetic facial images, with the ViT Patch-16 model performing best on this task with a class-averaged sensitivity, specificity, precision, and accuracy of 97.37%, 98.69%, 97.48%, and 98.25%, respectively. This observation was supported by further analysis of various image properties. We saw noticeable differences across the three category of images. This analysis can help us build better algorithms for facial image generation, and also shows that synthetic, deepfake and real face images are indeed three different classes.

We prove that any spectrum is equivalent to the nonconnective K-theory of a stable $\infty$-category. We use these results to construct a stable $\infty$-category $\mathcal{C}$ with a bounded t-structure such that $\operatorname{K}(\mathcal{C})$ is not equivalent to $\operatorname{K}(\mathcal{C}^\heartsuit)$, disproving a conjecture of Antieau, Gepner, and Heller., Comment: 17 pages