paper-with-me

Papers

Calibrating Deep Neural Network using Euclidean Distance

2024-10-23 · Wenhao Liang, Chang Dong, Liangwei Zheng, Zhengyang Li, Wei zhang, Weitong Chen

Uncertainty is a fundamental aspect of real-world scenarios, where perfect information is rarely available. Humans naturally develop complex internal models to navigate incomplete data and effectively respond to unforeseen or partially observed events. In machine learning, Focal Loss is commonly used to reduce misclassification rates by emphasizing hard-to-classify samples. However, it does not guarantee well-calibrated predicted probabilities and may result in models that are overconfident or underconfident. High calibration error indicates a misalignment between predicted probabilities and actual outcomes, affecting model reliability. This research introduces a novel loss function called Focal Calibration Loss (FCL), designed to improve probability calibration while retaining the advantages of Focal Loss in handling difficult samples. By minimizing the Euclidean norm through a strictly proper loss, FCL penalizes the instance-wise calibration error and constrains bounds. We provide theoretical validation for proposed method and apply it to calibrate CheXNet for potential deployment in web-based health-care systems. Extensive evaluations on various models and datasets demonstrate that our method achieves SOTA performance in both calibration and accuracy metrics.

📄 PDF Abstract BibTeX arXiv:2410.18321

Code (0)

등록된 구현이 없습니다.

Tasks

Navigate

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Kaiming Initialization 설명 없음
Average Pooling 설명 없음
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Batch Normalization 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Efficient Matrix Profile Computation Using Different Distance Functions

2019-01-17 · Reza Akbarinia, Bertrand Cloez

Matrix profile has been recently proposed as a promising technique to the problem of all-pairs-similarity search on time series. Efficient algorithms have been proposed for computing it, e.g., STAMP, STOMP and SCRIMP++. …

Time SeriesTime Series Analysis

VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

2024-08-30 · Juncan Deng, Shuaiting Li, Zeyu Wang, Hong Gu 외

The Diffusion Transformers Models (DiTs) have transitioned the network architecture from traditional UNets to transformers, demonstrating exceptional capabilities in image generation. Although DiTs have been widely appli…

GPUImage GenerationQuantizationVideo Generation

Tackling Early Sparse Gradients in Softmax Activation Using Leaky Squared Euclidean Distance

2018-11-27 · Wei Shen, Rujie Liu

Softmax activation is commonly used to output the probability distribution over categories based on certain distance metric. In scenarios like one-shot learning, the distance metric is often chosen to be squared Euclidea…

One-Shot Learning

Convergent Bounds on the Euclidean Distance

2011-12-01 · NeurIPS 2011 12 · Yoonho Hwang, Hee-Kap Ahn

Given a set V of n vectors in d-dimensional space, we provide an efficient method for computing quality upper and lower bounds of the Euclidean distances between a pair of the vectors in V . For this purpose, we define…

Deterministic Equivalent of the Log-Euclidean Distance between Sample Covariance Matrices

2024-08-08 · Xavier Mestre, Roberto Pereira

Log-Euclidean distances are commonly used to quantify the similarity between positive definite matrices using geometric considerations. This paper analyzes the behavior of this distance when it is used to measure closene…