Papers with Code 아카이브

Classifier calibration

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 1
보존된 평가 기록: 1

Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. The two common calibration metrics are Expected Calibration Error (ECE) and Maximum Calibration Error (MCE).

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/ENSTA-U2IS-AI/torch-uncertainty

공식 코드

Packed-Ensembles for Efficient Uncertainty Estimation

https://github.com/TailinZhou/FedFA

공식 코드

FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data

https://github.com/ToyotaCRDL/SimplexTS

공식 코드

Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex

https://github.com/annusha/lcwof

공식 코드

Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting

https://github.com/appliedai-initiative/classwise-calibration-experiments

공식 코드

Class-wise and reduced calibration methods

https://github.com/fabiankueppers/calibration-framework

공식 코드

Multivariate Confidence Calibration for Object Detection

https://github.com/hhhhedy/gfss-ekt

공식 코드

Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer

https://github.com/isotlaboratory/ClassifierCalibration-Code

공식 코드

Classifier Calibration: with application to threat scores in cybersecurity

https://github.com/libo-huang/PrePrompt

공식 코드

PrePrompt: Predictive prompting for class incremental learning

https://github.com/linusericsson/ssl-transfer

공식 코드

How Well Do Self-Supervised Models Transfer?

https://github.com/minhlong94/random-mixup

공식 코드

Expeditious Saliency-guided Mix-up through Random Gradient Thresholding

https://github.com/nikitadurasov/masksembles

공식 코드

Masksembles for Uncertainty Estimation

https://github.com/peterlipan/lmd

공식 코드

Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier Calibration

https://github.com/picekl/DanishFungiDataset

공식 코드

Danish Fungi 2020 -- Not Just Another Image Recognition Dataset

https://github.com/wkiri/simcalib

공식 코드

Hidden Heterogeneity: When to Choose Similarity-Based Calibration

https://github.com/zexilee/iccv-2023-fedetf

공식 코드

No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier

https://github.com/KarhouTam/FL-bench

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

https://github.com/ensta-u2is/torch-uncertainty

Masksembles for Uncertainty Estimation

https://github.com/krumpguo/fedvls

No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data

https://github.com/lightning-uq-box/lightning-uq-box

Masksembles for Uncertainty Estimation

https://github.com/weizheliu/cross-domain-crowd-counting

Masksembles for Uncertainty Estimation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.