FMG-Det: Foundation Model Guided Robust Object Detection
This addresses the challenge of inconsistent and noisy labeling in object detection, particularly impactful for applications requiring high accuracy with limited data, though it appears incremental as it builds on existing multiple instance learning and foundation model techniques.
The paper tackles the problem of noisy object detection annotations, which degrade model performance, by proposing FMG-Det, a method that uses foundation models to correct labels before training, achieving state-of-the-art results across multiple datasets in standard and few-shot scenarios.
Collecting high quality data for object detection tasks is challenging due to the inherent subjectivity in labeling the boundaries of an object. This makes it difficult to not only collect consistent annotations across a dataset but also to validate them, as no two annotators are likely to label the same object using the exact same coordinates. These challenges are further compounded when object boundaries are partially visible or blurred, which can be the case in many domains. Training on noisy annotations significantly degrades detector performance, rendering them unusable, particularly in few-shot settings, where just a few corrupted annotations can impact model performance. In this work, we propose FMG-Det, a simple, efficient methodology for training models with noisy annotations. More specifically, we propose combining a multiple instance learning (MIL) framework with a pre-processing pipeline that leverages powerful foundation models to correct labels prior to training. This pre-processing pipeline, along with slight modifications to the detector head, results in state-of-the-art performance across a number of datasets, for both standard and few-shot scenarios, while being much simpler and more efficient than other approaches.