Adversarial Focal Loss: Asking Your Discriminator for Hard Examples

07/15/2022
by   Chen Liu, et al.
13

Focal Loss has reached incredible popularity as it uses a simple technique to identify and utilize hard examples to achieve better performance on classification. However, this method does not easily generalize outside of classification tasks, such as in keypoint detection. In this paper, we propose a novel adaptation of Focal Loss for keypoint detection tasks, called Adversarial Focal Loss (AFL). AFL not only is semantically analogous to Focal loss, but also works as a plug-and-chug upgrade for arbitrary loss functions. While Focal Loss requires output from a classifier, AFL leverages a separate adversarial network to produce a difficulty score for each input. This difficulty score can then be used to dynamically prioritize learning on hard examples, even in absence of a classifier. In this work, we show AFL's effectiveness in enhancing existing methods in keypoint detection and verify its capability to re-weigh examples based on difficulty.

READ FULL TEXT

page 6

page 8

page 15

page 16

research
08/31/2021

A Novel Dataset for Keypoint Detection of quadruped Animals from Images

In this paper, we studied the problem of localizing a generic set of key...
research
05/01/2021

Lite-FPN for Keypoint-based Monocular 3D Object Detection

3D object detection with a single image is an essential and challenging ...
research
03/10/2021

Regressive Domain Adaptation for Unsupervised Keypoint Detection

Domain adaptation (DA) aims at transferring knowledge from a labeled sou...
research
12/09/2018

Theory of Curriculum Learning, with Convex Loss Functions

Curriculum Learning - the idea of teaching by gradually exposing the lea...
research
11/05/2020

Can Human Sex Be Learned Using Only 2D Body Keypoint Estimations?

In this paper, we analyze human male and female sex recognition problem ...
research
06/19/2014

R-CNNs for Pose Estimation and Action Detection

We present convolutional neural networks for the tasks of keypoint (pose...
research
03/24/2021

Loss based prior for the degrees of freedom of the Wishart distribution

In this paper we propose a novel method to deal with Vector Autoregressi...

Please sign up or login with your details

Forgot password? Click here to reset