The Importance of Anti-Aliasing in Tiny Object Detection

Jinlai Ning, Michael Spratling
Proceedings of the 15th Asian Conference on Machine Learning, PMLR 222:975-990, 2024.

Abstract

Tiny object detection has gained considerable attention in the research community owing to the frequent occurrence of tiny objects in numerous critical real-world scenarios. However, convolutional neural networks (CNNs) used as the backbone for object detection architectures typically neglect Nyquist’s sampling theorem during down-sampling operations, resulting in aliasing and degraded performance. This is likely to be a particular issue for tiny objects that occupy very few pixels and therefore have high spatial frequency features. This paper applied an existing approach WaveCNet for anti-aliasing to tiny object detection. WaveCNet addresses aliasing by replacing standard down-sampling processes in CNNs with Wavelet Pooling (WaveletPool) layers, effectively suppressing aliasing. We modify the original WaveCNet to apply WaveletPool in a consistent way in both pathways of the residual blocks in ResNets. Additionally, we also propose a bottom-heavy version of the backbone, which further improves the performance of tiny object detection while also reducing the required number of parameters by almost half. Experimental results on the TinyPerson, WiderFace, and DOTA datasets demonstrate the importance of anti-aliasing in tiny object detection and the effectiveness of the proposed method which achieves new state-of-the-art results on all three datasets. Codes and experiment results are released at \url{https://github.com/freshn/Anti-aliasing-Tiny-Object-Detection.git}.

Cite this Paper

BibTeX
@InProceedings{pmlr-v222-ning24a, title = {The Importance of Anti-Aliasing in Tiny Object Detection}, author = {Ning, Jinlai and Spratling, Michael}, booktitle = {Proceedings of the 15th Asian Conference on Machine Learning}, pages = {975--990}, year = {2024}, editor = {Yanıkoğlu, Berrin and Buntine, Wray}, volume = {222}, series = {Proceedings of Machine Learning Research}, month = {11--14 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v222/ning24a/ning24a.pdf}, url = {https://proceedings.mlr.press/v222/ning24a.html}, abstract = {Tiny object detection has gained considerable attention in the research community owing to the frequent occurrence of tiny objects in numerous critical real-world scenarios. However, convolutional neural networks (CNNs) used as the backbone for object detection architectures typically neglect Nyquist’s sampling theorem during down-sampling operations, resulting in aliasing and degraded performance. This is likely to be a particular issue for tiny objects that occupy very few pixels and therefore have high spatial frequency features. This paper applied an existing approach WaveCNet for anti-aliasing to tiny object detection. WaveCNet addresses aliasing by replacing standard down-sampling processes in CNNs with Wavelet Pooling (WaveletPool) layers, effectively suppressing aliasing. We modify the original WaveCNet to apply WaveletPool in a consistent way in both pathways of the residual blocks in ResNets. Additionally, we also propose a bottom-heavy version of the backbone, which further improves the performance of tiny object detection while also reducing the required number of parameters by almost half. Experimental results on the TinyPerson, WiderFace, and DOTA datasets demonstrate the importance of anti-aliasing in tiny object detection and the effectiveness of the proposed method which achieves new state-of-the-art results on all three datasets. Codes and experiment results are released at \url{https://github.com/freshn/Anti-aliasing-Tiny-Object-Detection.git}.} }
Endnote
%0 Conference Paper %T The Importance of Anti-Aliasing in Tiny Object Detection %A Jinlai Ning %A Michael Spratling %B Proceedings of the 15th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Berrin Yanıkoğlu %E Wray Buntine %F pmlr-v222-ning24a %I PMLR %P 975--990 %U https://proceedings.mlr.press/v222/ning24a.html %V 222 %X Tiny object detection has gained considerable attention in the research community owing to the frequent occurrence of tiny objects in numerous critical real-world scenarios. However, convolutional neural networks (CNNs) used as the backbone for object detection architectures typically neglect Nyquist’s sampling theorem during down-sampling operations, resulting in aliasing and degraded performance. This is likely to be a particular issue for tiny objects that occupy very few pixels and therefore have high spatial frequency features. This paper applied an existing approach WaveCNet for anti-aliasing to tiny object detection. WaveCNet addresses aliasing by replacing standard down-sampling processes in CNNs with Wavelet Pooling (WaveletPool) layers, effectively suppressing aliasing. We modify the original WaveCNet to apply WaveletPool in a consistent way in both pathways of the residual blocks in ResNets. Additionally, we also propose a bottom-heavy version of the backbone, which further improves the performance of tiny object detection while also reducing the required number of parameters by almost half. Experimental results on the TinyPerson, WiderFace, and DOTA datasets demonstrate the importance of anti-aliasing in tiny object detection and the effectiveness of the proposed method which achieves new state-of-the-art results on all three datasets. Codes and experiment results are released at \url{https://github.com/freshn/Anti-aliasing-Tiny-Object-Detection.git}.
APA
Ning, J. & Spratling, M.. (2024). The Importance of Anti-Aliasing in Tiny Object Detection. Proceedings of the 15th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 222:975-990 Available from https://proceedings.mlr.press/v222/ning24a.html.

Related Material