相关论文: Class Distance Weighted Cross-Entropy Loss for Ulc…

Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…

Within medical imaging segmentation, the Dice coefficient and Hausdorff-based metrics are standard measures of success for deep learning models. However, modern loss functions for medical image segmentation often only consider the Dice…

Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e.g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models. Since collecting new training…

The cross entropy (CE) method is a model based search method to solve optimization problems where the objective function has minimal structure. The Monte-Carlo version of the CE method employs the naive sample averaging technique which is…

Complementary-label learning (CLL) is widely used in weakly supervised classification, but it faces a significant challenge in real-world datasets when confronted with class-imbalanced training samples. In such scenarios, the number of…

Abdominal Aortic Calcification (AAC) is a known marker of asymptomatic Atherosclerotic Cardiovascular Diseases (ASCVDs). AAC can be observed on Vertebral Fracture Assessment (VFA) scans acquired using Dual-Energy X-ray Absorptiometry (DXA)…

Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, such as sample mining or pair weighting. The standard…

As language models grow ever larger, so do their vocabularies. This has shifted the memory footprint of LLMs during training disproportionately to one single layer: the cross-entropy in the loss computation. Cross-entropy builds up a logit…

All machine learning algorithms use a loss, cost, utility or reward function to encode the learning objective and oversee the learning process. This function that supervises learning is a frequently unrecognized hyperparameter that…

In observational studies, propensity scores are commonly estimated by maxi- mum likelihood but may fail to balance high-dimensional pre-treatment covariates even after specification search. We introduce a general framework that unifies and…

Energy-based models (EBMs) are generative models inspired by statistical physics with a wide range of applications in unsupervised learning. Their performance is best measured by the cross-entropy (CE) of the model distribution relative to…

Edge detection (ED) is a fundamental perceptual process in computer vision, forming the structural basis for high-level reasoning tasks such as segmentation, recognition, and scene understanding. Despite substantial progress achieved by…

Recently, the amount of GI tract datasets is introduced more and more by gathering from contests and challenges. The most common task needs to solve that is to classify images from the GI tract into various classes. However, the…

Weakly supervised methods, such as class activation maps (CAM) based, have been applied to achieve bleeding segmentation with low annotation efforts in Wireless Capsule Endoscopy (WCE) images. However, the CAM labels tend to be extremely…

Scalability is a major challenge in modern recommender systems. In sequential recommendations, full Cross-Entropy (CE) loss achieves state-of-the-art recommendation quality but consumes excessive GPU memory with large item catalogs,…

Medical image segmentation poses significant challenges due to class imbalance and the complex structure of medical images. To address these challenges, this study proposes YM-WML, a novel model for cardiac image segmentation. The model…

The vast majority of the outlet glaciers and ice streams of the polar ice sheets end in the ocean. Ice mass loss via calving of the glaciers into the ocean has increased over the last few decades. Information on the temporal variability of…

The top-k error is a common measure of performance in machine learning and computer vision. In practice, top-k classification is typically performed with deep neural networks trained with the cross-entropy loss. Theoretical results indeed…

In a clustered observational study, treatment is assigned to groups and all units within the group are exposed to the treatment. Here, we use a clustered observational study (COS) design to estimate the effectiveness of Magnet Nursing…

Synthesizing longitudinal medical images at controllable disease stages while preserving patient-specific anatomy is hindered by the entanglement of pathological textures and structural features. We address this challenge for ulcerative…