Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification

TL;DR

This paper introduces a recursive attention mechanism that iteratively refines focus on discriminative image parts, improving fine-grained classification accuracy without requiring additional annotations.

Contribution

It proposes a simple, interpretable attention model that mimics human visual focus, enhancing feature extraction for fine-grained image classification using only image-level labels.

Findings

Boosts classification accuracy by up to 2%

Provides interpretability of focus changes from coarse to fine details

Operates without bounding box or part annotations

Abstract

Deep Neural Network has shown great strides in the coarse-grained image classification task. It was in part due to its strong ability to extract discriminative feature representations from the images. However, the marginal visual difference between different classes in fine-grained images makes this very task harder. In this paper, we tried to focus on these marginal differences to extract more representative features. Similar to human vision, our network repetitively focuses on parts of images to spot small discriminative parts among the classes. Moreover, we show through interpretability techniques how our network focus changes from coarse to fine details. Through our experiments, we also show that a simple attention model can aggregate (weighted) these finer details to focus on the most dominant discriminative part of the image. Our network uses only image-level labels and does not need bounding box/part annotation information. Further, the simplicity of our network makes it an easy plug-n-play module. Apart from providing interpretability, our network boosts the performance (up to 2%) when compared to its baseline counterparts. Our codebase is available at https://github.com/TAMU-VITA/Focus-Longer-to-See-Better