Light-Net: Lightweight Object Detector

Yunbo Rao, Guo Yi, Junmin Xue, Jiansu Pu, Jianping Gou, Qiujie Wang, Qifei WangIEEE Access 2020 · OpenReview

Abstract

Currently, object detectors based on CNN, such as RetinaNet, Faster-RCNN, and the CornerNet series, achieve high performance but suffer from significant computational costs, high model complexity, and slow detection speeds. This paper proposes Light-Net, a new lightweight object detector that utilizes a density-based approach to merge anchor boxes. To optimize speed and cost, Light-Net employs multi-scale outputs to predict objects of varying sizes. Furthermore, a novel lightweight network model is introduced, featuring "separation convolutions" to improve efficiency without sacrificing performance. Experimental results on the MS-COCO 2014 dataset demonstrate a 20.9% mAP with a model size under 10MB, showcasing the superiority of the proposed method for resource-constrained environments.

Introduction

While deep learning has revolutionized object detection, state-of-the-art models like Faster R-CNN or RetinaNet are often too computationally expensive for real-time use on edge devices or mobile platforms. The authors identify two specific bottlenecks in existing lightweight detectors: inefficient anchor generation and high model complexity. Standard convolutional layers carry a heavy parameter load, and while depthwise separable convolutions help, there is still significant room to optimize feature extraction and fusion across different scales.

Methodology

Light-Net is a one-stage detector built on three primary pillars:

Density-Based Anchor Generation

Instead of traditional K-means clustering, which is often sensitive to initial conditions, the authors introduce a density-based merging approach. By using a distance function based on $1 - IOU$ (Intersection over Union), the algorithm finds the most representative bounding box shapes. This method is more stable and provides a deterministic set of priors compared to stochastic clustering.

Separation Convolution (Sep Block)

To reduce parameters, Light-Net replaces standard $N \times N$ convolutions with a "separation" strategy, decomposing them into $N \times 1$ and $1 \times N$ layers. This reduces the calculation cost significantly while maintaining the receptive field and descriptive power of the network.

Multi-Scale Output and Focal Loss

The network predicts objects at two different scales, using high-resolution features for small objects and semantically rich, low-resolution features for larger ones. To handle the extreme imbalance between foreground and background typical in one-stage detectors, the model employs Focal Loss to prevent the detector from being overwhelmed by "easy" negative samples.

Experimental Results

The model was trained from scratch on the MS-COCO 2014 dataset. Light-Net achieved a competitive 20.9% mAP. Notably, the Light-Net32 variant has a model size of only 7.3MB (approx. 7.66 GMacs) and an inference time of roughly 25ms on an NVIDIA GTX 1070 (~40 FPS).

Qualitative Analysis

The following figures demonstrate the detection capabilities of Light-Net on complex scenes from the MS-COCO dataset. While lightweight, the model successfully identifies a variety of objects in both indoor and outdoor settings.

Detection performance on a baseball scene, illustrating the model's ability to identify players and equipment.
Detection performance on a kitchen scene, demonstrating the model's capability in indoor environments with multiple object categories.

Conclusion

Light-Net offers a compelling trade-off between accuracy and efficiency. By rethinking anchor generation and convolutional architecture, the authors have created a detector suitable for real-time applications on mobile and edge devices. Future work will focus on increasing training iterations, applying advanced data augmentation, and exploring deeper versions of the Light-Net backbone for applications where the 10MB limit is less strict.

Summary updated

Abstract

Currently, object detectors based on CNN, such as RetinaNet, Faster-RCNN, CornerNet series, can achieve good performance, but have some common drawbacks, like large calculation cost, high model complexity and slow detection speed. In this paper, a new lightweight object detector is proposed, which adopted a density-based approach to merge the real boxes. To reduce calculation cost and improve detection speed, the tactic of multi-scale output is adopted to predict objects of different sizes with features of different scales. Furthermore, a new lightweight network model is proposed, which can show better performance in computation, FPS, and model complexity. Meanwhile, the separation of convolution is used to improve the basic convolution layer, which can achieve better results under the same number of filters. In the experiments, we verified the capability of our methods based on ablation experiment and model evaluation, which demonstrates the superiority of our method. Moreover, we have also conducted deep network and multichannel experiments on MS-COCO2014 datasets and achieved 20.9% mAP performance.
BibTeX
@inproceedings{rao2020light,
  author = {Yunbo Rao and Guo Yi and Junmin Xue and Jiansu Pu and Jianping Gou and Qiujie Wang and Qifei Wang},
  title = {{Light-Net: Lightweight Object Detector}},
  booktitle = {IEEE Access},
  year = {2020},
  url = {https://openreview.net/forum?id=KZgp27UZQ-},
}
Figure