NL-FCOS: Improving FCOS through Non-Local Modules for Object Detection

TL;DR

This paper introduces NL-FCOS, an anchor-free object detection model enhanced with non-local modules to mimic perceptual grouping, achieving state-of-the-art results in clothing detection and handwritten amount recognition.

Contribution

It proposes integrating non-local modules into FCOS to improve feature representation by modeling perceptual grouping without increasing inference time.

Findings

State-of-the-art performance in clothing detection.

Effective enhancement for handwritten amount recognition.

Non-local modules boost feature map cooperation.

Abstract

During the last years, we have seen significant advances in the object detection task, mainly due to the outperforming results of convolutional neural networks. In this vein, anchor-based models have achieved the best results. However, these models require prior information about the aspect and scales of target objects, needing more hyperparameters to fit. In addition, using anchors to fit bounding boxes seems far from how our visual system does the same visual task. Instead, our visual system uses the interactions of different scene parts to semantically identify objects, called perceptual grouping. An object detection methodology closer to the natural model is anchor-free detection, where models like FCOS or Centernet have shown competitive results, but these have not yet exploited the concept of perceptual grouping. Therefore, to increase the effectiveness of anchor-free models keeping the inference time low, we propose to add non-local attention (NL modules) modules to boost the feature map of the underlying backbone. NL modules implement the perceptual grouping mechanism, allowing receptive fields to cooperate in visual representation learning. We show that non-local modules combined with an FCOS head (NL-FCOS) are practical and efficient. Thus, we establish state-of-the-art performance in clothing detection and handwritten amount recognition problems.