GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition

05/01/2021
by   Bo Liu, et al.
0

The problem of long-tailed recognition, where the number of examples per class is highly unbalanced, is considered. It is hypothesized that the well known tendency of standard classifier training to overfit to popular classes can be exploited for effective transfer learning. Rather than eliminating this overfitting, e.g. by adopting popular class-balanced sampling methods, the learning algorithm should instead leverage this overfitting to transfer geometric information from popular to low-shot classes. A new classifier architecture, GistNet, is proposed to support this goal, using constellations of classifier parameters to encode the class geometry. A new learning algorithm is then proposed for GeometrIc Structure Transfer (GIST), with resort to a combination of loss functions that combine class-balanced and random sampling to guarantee that, while overfitting to the popular classes is restricted to geometric parameters, it is leveraged to transfer class geometry from popular to few-shot classes. This enables better generalization for few-shot classes without the need for the manual specification of class weights, or even the explicit grouping of classes into different types. Experiments on two popular long-tailed recognition datasets show that GistNet outperforms existing solutions to this problem.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/01/2021

Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition

The problem of long-tailed recognition, where the number of examples per...
research
04/12/2021

Class-Balanced Distillation for Long-Tailed Visual Recognition

Real-world imagery is often characterized by a significant imbalance of ...
research
09/15/2020

The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis

Long-tailed relation classification is a challenging problem as the head...
research
08/06/2023

Novel Class Discovery for Long-tailed Recognition

While the novel class discovery has achieved great success, existing met...
research
09/07/2022

Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition

Long-tailed datasets, where head classes comprise much more training sam...
research
04/20/2021

A novel three-stage training strategy for long-tailed classification

The long-tailed distribution datasets poses great challenges for deep le...
research
11/07/2018

Prototypical Clustering Networks for Dermatological Disease Diagnosis

We consider the problem of image classification for the purpose of aidin...

Please sign up or login with your details

Forgot password? Click here to reset