Classification Consistency

3 papers with code • 0 benchmarks • 0 datasets

How often two shifts of the same image are classified the same

( Image credit: Antialiased CNNs )

Most implemented papers

Making Convolutional Networks Shift-Invariant Again

adobe/antialiased-cnns 25 Apr 2019

The well-known signal processing fix is anti-aliasing by low-pass filtering before downsampling.

Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity

optimization-ai/icml2023_ldr 30 Dec 2021

We study a family of loss functions named label-distributionally robust (LDR) losses for multi-class classification that are formulated from distributionally robust optimization (DRO) perspective, where the uncertainty in the given label information are modeled and captured by taking the worse case of distributional weights.

End-to-End Semi-Supervised Learning for Video Action Detection

AKASH2907/End-to-End-Semi-Supervised-Learning-for-Video-Action-Detection CVPR 2022

In this work, we focus on semi-supervised learning for video action detection which utilizes both labeled as well as unlabeled data.