DeepAI AI Chat
Log In Sign Up

Learning with Label Noise for Image Retrieval by Selecting Interactions

12/20/2021
by   Sarah Ibrahimi, et al.
0

Learning with noisy labels is an active research area for image classification. However, the effect of noisy labels on image retrieval has been less studied. In this work, we propose a noise-resistant method for image retrieval named Teacher-based Selection of Interactions, T-SINT, which identifies noisy interactions, ie. elements in the distance matrix, and selects correct positive and negative interactions to be considered in the retrieval loss by using a teacher-based training setup which contributes to the stability. As a result, it consistently outperforms state-of-the-art methods on high noise rates across benchmark datasets with synthetic noise and more realistic noise.

READ FULL TEXT

page 1

page 3

07/23/2021

A Realistic Simulation Framework for Learning with Label Noise

We propose a simulation framework for generating realistic instance-depe...
03/17/2021

Improved Deep Classwise Hashing With Centers Similarity Learning for Image Retrieval

Deep supervised hashing for image retrieval has attracted researchers' a...
02/01/2021

Learning to Combat Noisy Labels via Classification Margins

A deep neural network trained on noisy labels is known to quickly lose i...
10/25/2016

End-to-end Learning of Deep Visual Representations for Image Retrieval

While deep learning has become a key ingredient in the top performing me...
05/27/2021

Training Classifiers that are Universally Robust to All Label Noise Levels

For classification tasks, deep neural networks are prone to overfitting ...
09/27/2017

Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction

In this paper, we present a method to learn a visual representation adap...
05/04/2017

Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labels

Noisy PN learning is the problem of binary classification when training ...