# Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes

## TL;DR

This paper introduces a novel label transfer model that leverages both intermodal and intramodal processes to improve image classification, especially for unseen classes, by utilizing text data and mitigating noise issues.

## Contribution

It develops a combined intermodal and intramodal label transfer framework that enhances zero-shot image classification by learning functional relationships between text and image features.

## Key findings

- Effective in zero-shot learning scenarios
- Outperforms existing algorithms in image classification tasks
- Mitigates noise in label transfer processes

## Abstract

In this paper, we present a label transfer model from texts to images for image classification tasks. The problem of image classification is often much more challenging than text classification. On one hand, labeled text data is more widely available than the labeled images for classification tasks. On the other hand, text data tends to have natural semantic interpretability, and they are often more directly related to class labels. On the contrary, the image features are not directly related to concepts inherent in class labels. One of our goals in this paper is to develop a model for revealing the functional relationships between text and image features as to directly transfer intermodal and intramodal labels to annotate the images. This is implemented by learning a transfer function as a bridge to propagate the labels between two multimodal spaces. However, the intermodal label transfers could be undermined by blindly transferring the labels of noisy texts to annotate images. To mitigate this problem, we present an intramodal label transfer process, which complements the intermodal label transfer by transferring the image labels instead when relevant text is absent from the source corpus. In addition, we generalize the inter-modal label transfer to zero-shot learning scenario where there are only text examples available to label unseen classes of images without any positive image examples. We evaluate our algorithm on an image classification task and show the effectiveness with respect to the other compared algorithms.