Abstract :

Visual object detection is an artificial intelligence technique that locates specific objects from images, which is of great significance for practical applications. However, training general object detection models require many manually annotated images, bringing more labour and time cost. In order to improve the adaptability of the object detection model to the data environment changes, this paper proposes a self-learning object detection system based on high-reliability sample mining. We first train a SampleNet that can better mine reliable training samples from unlabeled data. We then use the combination of SampleNet and the basic object detection model to build a complementary residual training framework, continuously improving the sample mining ability and object detection tasks during the training process. The experimental results show that SampleNet can stably provide reliable pseudo samples for model training, and the complementary residual training framework improves the performance of basic object detection tasks.

---

Keywords :

Complementary residual learning, Object detection, Sample mining.

---

References :

1. Zhao, Z. Q., Zheng, P., Xu, S. T., & Wu, X. (2019). Object detection with deep learning: A review. IEEE transactions on neural networks and learning systems, 30(11), 3212-3232.
2. Farrell, M. H., Liang, T., & Misra, S. (2021). Deep neural networks for estimation and inference. Econometrica, 89(1), 181-213.
3. Hoiem, D., Divvala, S. K., & Hays, J. H. (2009). Pascal VOC 2008 challenge. World Literature Today, 24.
4. Li, H., Ota, K., & Dong, M. (2018). Learning IoT in edge: Deep learning for the Internet of Things with edge computing. IEEE network, 32(1), 96-101.
5. Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., … & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861.
6. Canévet, O., & Fleuret, F. (2015, February). Efficient sample mining for object detection. In Asian Conference on Machine Learning (pp. 48-63). PMLR.
7. Wang, K., Yan, X., Zhang, D., Zhang, L., & Lin, L. Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection.
8. Niitani, Y., Akiba, T., Kerola, T., Ogawa, T., Sano, S., & Suzuki, S. (2018). Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects. arXiv preprint arXiv:1811.10862.
9. Shimoda, W., & Yanai, K. (2019). Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation. arXiv preprint arXiv:1911.01370.
10. Wei, Y., Liang, X., Chen, Y., Shen, X., Cheng, M. M., Feng, J., … & Yan, S. (2015). STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation. arXiv preprint arXiv:1509.03150.
11. Zhang, Y., Bai, Y., Ding, M., Li, Y., & Ghanem, B. (2018). Weakly-supervised object detection via mining pseudo ground truth bounding-boxes.
12. Katircioglu, I., Rhodin, H., Constantin, V., Spörri, J., Salzmann, M., & Fua, P. (2019). Self-supervised Training of Proposal-based Segmentation via Background Prediction.
13. Kim, S., Choi, J., Kim, T., & Kim, C. (2019). Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection. arXiv e-prints, arXiv-1909.
14. Song, Z., Chen, Q., Huang, Z., Hua, Y., & Yan, S. (2011). Contextualizing object detection and classification.
15. Lee, W., Na, J., & Kim, G. (2019, June). Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 4979-4988). IEEE Computer Society.
16. Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.