# Automatic Image Annotation via Label Transfer in the Semantic Space

arXiv: https://arxiv.org/abs/1605.04770 · HTML: https://mlsanity.com/paper/1605.04770/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2016.

## Built on by (most cited first, 3 of 3)

- [A survey of image labelling for computer vision applications](https://mlsanity.com/paper/2104.08885/) (2021)
- [Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.10892/) (2022)
- [Automatic Image Annotation (AIA) of AlmondNet-20 Method for Almond Detection by Improved CNN-based Model](https://mlsanity.com/paper/2408.11253/) (2024)

## Abstract (arXiv)

Automatic image annotation is among the fundamental problems in computer vision and pattern recognition, and it is becoming increasingly important in order to develop algorithms that are able to search and browse large-scale image collections. In this paper, we propose a label propagation framework based on Kernel Canonical Correlation Analysis (KCCA), which builds a latent semantic space where correlation of visual and textual features are well preserved into a semantic embedding. The proposed approach is robust and can work either when the training set is well annotated by experts, as well as when it is noisy such as in the case of user-generated tags in social media. We report extensive results on four popular datasets. Our results show that our KCCA-based framework can be applied to several state-of-the-art label transfer methods to obtain significant improvements. Our approach works even with the noisy tags of social users, provided that appropriate denoising is performed. Experiments on a large scale setting show that our method can provide some benefits even when the semantic space is estimated on a subset of training images.