The Importance of Anti-Aliasing in Tiny Object Detection

TL;DR

This paper demonstrates that applying anti-aliasing techniques, specifically Wavelet Pooling, significantly improves tiny object detection performance in CNNs, achieving state-of-the-art results across multiple datasets.

Contribution

The paper introduces a modified WaveCNet with consistent WaveletPool application and a bottom-heavy backbone, enhancing tiny object detection while reducing model complexity.

Findings

Anti-aliasing improves detection accuracy for tiny objects.

Wavelet Pooling effectively suppresses aliasing in CNNs.

Proposed methods outperform existing approaches on multiple datasets.

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 https://github.com/freshn/Anti-aliasing-Tiny-Object-Detection.git.