Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones

01/23/2021
by   Huafeng Liu, et al.
0

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention. However, the presence of label noise and hard examples in web images are two obstacles for training robust fine-grained recognition models. Therefore, in this paper, we propose a novel approach for removing irrelevant samples from real-world web images during training, while employing useful hard examples to update the network. Thus, our approach can alleviate the harmful effects of irrelevant noisy web images and hard examples to achieve better performance. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is far superior to current state-of-the-art web-supervised methods.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 2

page 4

page 5

page 6

page 7

page 8

page 9

page 11

08/06/2020

Data-driven Meta-set Based Fine-Grained Visual Classification

Constructing fine-grained image datasets typically requires domain-speci...
11/20/2015

The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition

Current approaches for fine-grained recognition do the following: First,...
11/30/2016

Attend in groups: a weakly-supervised deep learning framework for learning from web data

Large-scale datasets have driven the rapid development of deep neural ne...
08/06/2020

Salvage Reusable Samples from Noisy Data for Robust Learning

Due to the existence of label noise in web images and the high memorizat...
12/21/2018

Learning from Web Data: the Benefit of Unsupervised Object Localization

Annotating a large number of training images is very time-consuming. In ...
12/29/2020

Tips and Tricks for Webly-Supervised Fine-Grained Recognition: Learning from the WebFG 2020 Challenge

WebFG 2020 is an international challenge hosted by Nanjing University of...
06/28/2019

ProtoNet: Learning from Web Data with Memory

Learning from web data has attracted lots of research interest in recent...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.