What Happens Without Background? Constructing Foreground-Only Data for Fine-Grained Tasks

TL;DR

This paper introduces a pipeline using SAM and Detic to create foreground-only datasets for fine-grained recognition, aiming to improve model focus on discriminative features and reduce background noise influence.

Contribution

The authors propose a novel preprocessing pipeline that generates foreground-only datasets for fine-grained tasks, enhancing model performance by eliminating background distractions.

Findings

Foreground-only datasets improve recognition accuracy.

Preprocessing with SAM and Detic enhances model focus.

Potential for expanding to other modalities.

Abstract

Fine-grained recognition, a pivotal task in visual signal processing, aims to distinguish between similar subclasses based on discriminative information present in samples. However, prevailing methods often erroneously focus on background areas, neglecting the capture of genuinely effective discriminative information from the subject, thus impeding practical application. To facilitate research into the impact of background noise on models and enhance their ability to concentrate on the subject's discriminative features, we propose an engineered pipeline that leverages the capabilities of SAM and Detic to create fine-grained datasets with only foreground subjects, devoid of background. Extensive cross-experiments validate this approach as a preprocessing step prior to training, enhancing algorithmic performance and holding potential for further modal expansion of the data.