# Iterative Object and Part Transfer for Fine-Grained Recognition

## TL;DR

This paper introduces a nonparametric, data-driven iterative transfer method for object and part localization in fine-grained recognition, improving accuracy and scalability over traditional bottom-up approaches.

## Contribution

It proposes a novel iterative transfer strategy that refines object and part localization by leveraging similar images, reducing computational costs and enhancing recognition performance.

## Key findings

- Achieves superior accuracy on CUB200-2011 and Birdsnap datasets.
- Outperforms many state-of-the-art methods including those with manual annotations.
- Demonstrates scalable localization without extensive region proposals.

## Abstract

The aim of fine-grained recognition is to identify sub-ordinate categories in images like different species of birds. Existing works have confirmed that, in order to capture the subtle differences across the categories, automatic localization of objects and parts is critical. Most approaches for object and part localization relied on the bottom-up pipeline, where thousands of region proposals are generated and then filtered by pre-trained object/part models. This is computationally expensive and not scalable once the number of objects/parts becomes large. In this paper, we propose a nonparametric data-driven method for object and part localization. Given an unlabeled test image, our approach transfers annotations from a few similar images retrieved in the training set. In particular, we propose an iterative transfer strategy that gradually refine the predicted bounding boxes. Based on the located objects and parts, deep convolutional features are extracted for recognition. We evaluate our approach on the widely-used CUB200-2011 dataset and a new and large dataset called Birdsnap. On both datasets, we achieve better results than many state-of-the-art approaches, including a few using oracle (manually annotated) bounding boxes in the test images.