A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
The paper introduces metrics to quantify information discarding in DNNs.
FCDD improves image anomaly detection without post-hoc explainers.
Improves image quality in generative models by estimating pixel-wise aleatoric uncertainty.
Lazy labels enable deep learning for microscopy segmentation without full annotation.
Anomaly detection scores from VAE gradients improve tumor detection.
Pixel-wise relevance method shows how CNNs classify faces, varying across datasets and tasks.
InstaHide encrypts images for privacy in distributed learning.
A new method for spotting symbols in CAD images reduces annotation costs and improves accuracy.
In this work we propose a method for anatomical data augmentation that is based on using slices of computed tomography (CT) examinations that are adjacent to labeled slices as another resource of labeled data for training the network. The extended labeled data is used to train a U-net network for a pixel-wise classific…
Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the approximations to the posterior flexible and accurate, leading to tremendous progress. Howe…
Semantic boundary and edge detection aims at simultaneously detecting object edge pixels in images and assigning class labels to them. Systematic training of predictors for this task requires the labeling of edges in images which is a particularly tedious task. We propose a novel strategy for solving this task, when pi…
Separating a singing voice from its music accompaniment remains an important challenge in the field of music information retrieval. We present a unique neural network approach inspired by a technique that has revolutionized the field of vision: pixel-wise image classification, which we combine with cross entropy loss a…
Generative model creates realistic scenes from pixel-wise labels.
Paper evaluates CNN-based facial landmark detection methods.
This paper explores the trade-off between spatial and adversarial robustness in neural networks.
Graph U-Nets improve graph representation learning.
Magnetic resonance image (MRI) reconstruction is a severely ill-posed linear inverse task demanding time and resource intensive computations that can substantially trade off {\it accuracy} for {\it speed} in real-time imaging. In addition, state-of-the-art compressed sensing (CS) analytics are not cognizant of the imag…
We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound. We provide conditions under which they recover the data distribution and learn latent features, and formally show that common issues such as blurry samples and uninformative latent feat…
RGI improves robustness of GAN-inversion for image restoration and anomaly detection.
We present a neural network architecture based upon the Autoencoder (AE) and Generative Adversarial Network (GAN) that promotes a convex latent distribution by training adversarially on latent space interpolations. By using an AE as both the generator and discriminator of a GAN, we pass a pixel-wise error function acro…
RankSEG-RMA improves semantic segmentation efficiency and applicability.
Flow-SSN improves segmentation efficiency and accuracy.
Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based auto encoders have shown great potential in detecting anomalies in medical images. However, state-of-the-art anomaly scores are still based on the reconstruction error, which lacks in two e…
We propose UOLO, a novel framework for the simultaneous detection and segmentation of structures of interest in medical images. UOLO consists of an object segmentation module which intermediate abstract representations are processed and used as input for object detection. The resulting system is optimized simultaneousl…
Background-Foreground classification is a well-studied problem in computer vision. Due to the pixel-wise nature of modeling and processing in the algorithm, it is usually difficult to satisfy real-time constraints. There is a trade-off between the speed (because of model complexity) and accuracy. Inspired by the reject…
SaR-SVM-STV improves hyperspectral image classification with shape-adaptive reconstruction and denoising.
The key idea of current deep learning methods for dense prediction is to apply a model on a regular patch centered on each pixel to make pixel-wise predictions. These methods are limited in the sense that the patches are determined by network architecture instead of learned from data. In this work, we propose the dense…
Novel framework monitors cardiac image segmentation models in real-time.
Deep Leakage from Gradients can reveal private training data from shared gradients.
Pixel-wise classification, where each pixel is assigned to a predefined class, is one of the most important procedures in hyperspectral image (HSI) analysis. By representing a test pixel as a linear combination of a small subset of labeled pixels, a sparse representation classifier (SRC) gives rather plausible results …
Method estimates uncertainty in CT reconstructions.
Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correlate poorly with the …
We first, introduce a deep learning based framework named as DeepIrisNet2 for visible spectrum and NIR Iris representation. The framework can work without classical iris normalization step or very accurate iris segmentation; allowing to work under non-ideal situation. The framework contains spatial transformer layers t…
SLUG method detects bias and out-of-distribution content in generative models.
Antithetic noise improves diffusion models' uncertainty quantification.
Improved flow-based models capture dependencies better with multi-scale autoregressive priors.
DVNet efficiently segments large neurovascular datasets using skip connections.
Paper describes a video surveillance system for highway traffic events.
CBDA improves active learning for semantic segmentation, especially with imbalanced classes.
Paper presents a method to detect out-of-distribution spectra in intra-operative functional imaging.
A deep learning framework separates overlapping nuclei in histology images.
As part of autonomous car driving systems, semantic segmentation is an essential component to obtain a full understanding of the car's environment. One difficulty, that occurs while training neural networks for this purpose, is class imbalance of training data. Consequently, a neural network trained on unbalanced data …
Study detects boundaries in unlabeled noisy images without labels.
We propose a method to classify cardiac pathology based on a novel approach to extract image derived features to characterize the shape and motion of the heart. An original semi-supervised learning procedure, which makes efficient use of a large amount of non-segmented images and a small amount of images segmented manu…
Paper proposes structured semantic perturbations to improve adversarial attacks.
Network deconvolution removes redundant data to improve neural network performance.
Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile (e.g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help displace objects to make pushing movements more precise and collision-fr…
We present a method that "meta" classifies whether seg-ments predicted by a semantic segmentation neural networkintersect with the ground truth. For this purpose, we employ measures of dispersion for predicted pixel-wise class probability distributions, like classification entropy, that yield heat maps of the input sce…