DeepAI AI Chat
Log In Sign Up

Learning with Label Noise for Image Retrieval by Selecting Interactions

by   Sarah Ibrahimi, et al.

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.


page 1

page 3


A Realistic Simulation Framework for Learning with Label Noise

We propose a simulation framework for generating realistic instance-depe...

Improved Deep Classwise Hashing With Centers Similarity Learning for Image Retrieval

Deep supervised hashing for image retrieval has attracted researchers' a...

Learning to Combat Noisy Labels via Classification Margins

A deep neural network trained on noisy labels is known to quickly lose i...

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

While deep learning has become a key ingredient in the top performing me...

Training Classifiers that are Universally Robust to All Label Noise Levels

For classification tasks, deep neural networks are prone to overfitting ...

Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction

In this paper, we present a method to learn a visual representation adap...

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

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