Efficient Fine-Grained Object Detection
21
AP0.5:0.95 : 29.5 AP0.5:0.95 : 25.4 AP0.5:0.95 : 29.1 AP0.5:0.95 : 37.8
(a)
(b)
(c)
(d)
Fig. 2. Detection performance and AP scores for the class: screws. (a) Baseline (b)
Cascade (c) EA-CNNP w/ Cascade (d) EA-CNNC w/ Cascade
4 Conclusions
In this work an anchoring mechanism utilising heuristic information is proposed;
its ability to generate candidate regions that align better with the small-sized
ground-truth targets discloses the potential of improving the detection of small
objects that current two-stage state-of-the-art algorithms struggle with. The
experiments on the PC-Tower disassembly dataset consisted of challenging smallsized components (e.g. screws), exhibit promising results. As future work, integrating the edge anchors into an attention-like mechanism, is considered, while
experiments will be further extended using different types of WEEE devices.
Acknowledgments. This work was supported by the European Commission under
contract H2020-820742 HR-Recycler.
References
1. Axenopoulos, A., et al.: A hybrid human-robot collaborative environment for recycling electrical and electronic equipment. In: 2019 IEEE SmartWorld, Ubiquitous
Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing &
Communications, Cloud & Big Data Computing, Internet of People and Smart City
Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), pp. 1754–
1759. IEEE (2019)
2. Cai, Z., Vasconcelos, N.: Cascade R-CNN: high quality object detection and
instance segmentation. IEEE Trans. Pattern Analy. Mach. Intell. (2019). https://
doi.org/10.1109/tpami.2019.2956516
3. He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
4. Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S.: Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE Conference
on Computer Vision and Pattern Recognition, pp. 1222–1230 (2017)
5. Lin, T.Y., Doll´ ar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature
pyramid networks for object detection. In: Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
6. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D.,
Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp.
740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1 48
7. Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe,
N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham
(2016). https://doi.org/10.1007/978-3-319-46448-0 2
21
AP0.5:0.95 : 29.5 AP0.5:0.95 : 25.4 AP0.5:0.95 : 29.1 AP0.5:0.95 : 37.8
(a)
(b)
(c)
(d)
Fig. 2. Detection performance and AP scores for the class: screws. (a) Baseline (b)
Cascade (c) EA-CNNP w/ Cascade (d) EA-CNNC w/ Cascade
4 Conclusions
In this work an anchoring mechanism utilising heuristic information is proposed;
its ability to generate candidate regions that align better with the small-sized
ground-truth targets discloses the potential of improving the detection of small
objects that current two-stage state-of-the-art algorithms struggle with. The
experiments on the PC-Tower disassembly dataset consisted of challenging smallsized components (e.g. screws), exhibit promising results. As future work, integrating the edge anchors into an attention-like mechanism, is considered, while
experiments will be further extended using different types of WEEE devices.
Acknowledgments. This work was supported by the European Commission under
contract H2020-820742 HR-Recycler.
References
1. Axenopoulos, A., et al.: A hybrid human-robot collaborative environment for recycling electrical and electronic equipment. In: 2019 IEEE SmartWorld, Ubiquitous
Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing &
Communications, Cloud & Big Data Computing, Internet of People and Smart City
Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), pp. 1754–
1759. IEEE (2019)
2. Cai, Z., Vasconcelos, N.: Cascade R-CNN: high quality object detection and
instance segmentation. IEEE Trans. Pattern Analy. Mach. Intell. (2019). https://
doi.org/10.1109/tpami.2019.2956516
3. He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: The IEEE International Conference on Computer Vision (ICCV), October 2017
4. Li, J., Liang, X., Wei, Y., Xu, T., Feng, J., Yan, S.: Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE Conference
on Computer Vision and Pattern Recognition, pp. 1222–1230 (2017)
5. Lin, T.Y., Doll´ ar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature
pyramid networks for object detection. In: Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
6. Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D.,
Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp.
740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1 48
7. Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe,
N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham
(2016). https://doi.org/10.1007/978-3-319-46448-0 2