CaltechAUTHORS
  A Caltech Library Service

The Devil is in the Tails: Fine-grained Classification in the Wild

Van Horn, Grant and Perona, Pietro (2017) The Devil is in the Tails: Fine-grained Classification in the Wild. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20190327-085920615

[img] PDF - Submitted Version
See Usage Policy.

3009Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190327-085920615

Abstract

The world is long-tailed. What does this mean for computer vision and visual recognition? The main two implications are (1) the number of categories we need to consider in applications can be very large, and (2) the number of training examples for most categories can be very small. Current visual recognition algorithms have achieved excellent classification accuracy. However, they require many training examples to reach peak performance, which suggests that long-tailed distributions will not be dealt with well. We analyze this question in the context of eBird, a large fine-grained classification dataset, and a state-of-the-art deep network classification algorithm. We find that (a) peak classification performance on well-represented categories is excellent, (b) given enough data, classification performance suffers only minimally from an increase in the number of classes, (c) classification performance decays precipitously as the number of training examples decreases, (d) surprisingly, transfer learning is virtually absent in current methods. Our findings suggest that our community should come to grips with the question of long tails.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/1709.01450arXivDiscussion Paper
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2017. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
Record Number:CaltechAUTHORS:20190327-085920615
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190327-085920615
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94201
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:27 Mar 2019 17:00
Last Modified:03 Oct 2019 21:01

Repository Staff Only: item control page