Papers Class-Specific Performance

“Class-Specific Performance” 태그가 달린 논문 3편 · 필터 해제

Narrowing Class-Wise Robustness Gaps in Adversarial Training

2025-03-20 · Fatemeh Amerehi, Patrick Healy

Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve robustness to worst-case distribution shif…

Adversarial Robustness Class-Specific Performance Data Augmentation

GuideBP: Guiding Backpropagation Through Weaker Pathways of Parallel Logits

2021-04-23 · Bodhisatwa Mandal, Swarnendu Ghosh, Teresa Gonçalves, Paulo Quaresma 외

Convolutional neural networks often generate multiple logits and use simple techniques like addition or averaging for loss computation. But this allows gradients to be distributed equally among all paths. The proposed ap…

Class-Specific Performance

An Efficient Convolutional Neural Network for Coronary Heart Disease Prediction

2019-09-01 · Aniruddha Dutta, Tamal Batabyal, Meheli Basu, Scott T. Acton

This study proposes an efficient neural network with convolutional layers to classify significantly class-imbalanced clinical data. The data are curated from the National Health and Nutritional Examination Survey (NHANES…

Class-Specific Performance Disease Prediction Efficient Neural Network General Classification