Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement

Sheng Xu, Mingze Wang, Yanjing Li, Mingbao Lin, Baochang Zhang, David Doermann, Xiao Sun
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:55337-55347, 2024.

Abstract

1-bit detectors show impressive performance comparable to their real-valued counterparts when detecting commonly sized objects while exhibiting significant performance degradation on tiny objects. The challenge stems from the fact that high-level features extracted by 1-bit convolutions seem less compelling to reveal the discriminative foreground features. To address these issues, we introduce a Discriminative Feature Refinement method for 1-bit Detectors (DFR-Det), aiming to enhance the discriminative ability of foreground representation for tiny objects in aerial images. This is accomplished by refining the feature representation using an information bottleneck (IB) to achieve a distinctive representation of tiny objects. Specifically, we introduce a new decoder with a foreground mask, aiming to enhance the discriminative ability of high-level features for the target but suppress the background impact. Additionally, our decoder is simple but effective and can be easily mounted on existing detectors without extra burden added to the inference procedure. Extensive experiments on various tiny object detection (TOD) tasks demonstrate DFR-Det’s superiority over state-of-the-art 1-bit detectors. For example, 1-bit FCOS achieved by DFR-Det achieves the 12.8% AP on AI-TOD dataset, approaching the performance of the real-valued counterpart.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-xu24z, title = {Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement}, author = {Xu, Sheng and Wang, Mingze and Li, Yanjing and Lin, Mingbao and Zhang, Baochang and Doermann, David and Sun, Xiao}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {55337--55347}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/xu24z/xu24z.pdf}, url = {https://proceedings.mlr.press/v235/xu24z.html}, abstract = {1-bit detectors show impressive performance comparable to their real-valued counterparts when detecting commonly sized objects while exhibiting significant performance degradation on tiny objects. The challenge stems from the fact that high-level features extracted by 1-bit convolutions seem less compelling to reveal the discriminative foreground features. To address these issues, we introduce a Discriminative Feature Refinement method for 1-bit Detectors (DFR-Det), aiming to enhance the discriminative ability of foreground representation for tiny objects in aerial images. This is accomplished by refining the feature representation using an information bottleneck (IB) to achieve a distinctive representation of tiny objects. Specifically, we introduce a new decoder with a foreground mask, aiming to enhance the discriminative ability of high-level features for the target but suppress the background impact. Additionally, our decoder is simple but effective and can be easily mounted on existing detectors without extra burden added to the inference procedure. Extensive experiments on various tiny object detection (TOD) tasks demonstrate DFR-Det’s superiority over state-of-the-art 1-bit detectors. For example, 1-bit FCOS achieved by DFR-Det achieves the 12.8% AP on AI-TOD dataset, approaching the performance of the real-valued counterpart.} }
Endnote
%0 Conference Paper %T Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement %A Sheng Xu %A Mingze Wang %A Yanjing Li %A Mingbao Lin %A Baochang Zhang %A David Doermann %A Xiao Sun %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-xu24z %I PMLR %P 55337--55347 %U https://proceedings.mlr.press/v235/xu24z.html %V 235 %X 1-bit detectors show impressive performance comparable to their real-valued counterparts when detecting commonly sized objects while exhibiting significant performance degradation on tiny objects. The challenge stems from the fact that high-level features extracted by 1-bit convolutions seem less compelling to reveal the discriminative foreground features. To address these issues, we introduce a Discriminative Feature Refinement method for 1-bit Detectors (DFR-Det), aiming to enhance the discriminative ability of foreground representation for tiny objects in aerial images. This is accomplished by refining the feature representation using an information bottleneck (IB) to achieve a distinctive representation of tiny objects. Specifically, we introduce a new decoder with a foreground mask, aiming to enhance the discriminative ability of high-level features for the target but suppress the background impact. Additionally, our decoder is simple but effective and can be easily mounted on existing detectors without extra burden added to the inference procedure. Extensive experiments on various tiny object detection (TOD) tasks demonstrate DFR-Det’s superiority over state-of-the-art 1-bit detectors. For example, 1-bit FCOS achieved by DFR-Det achieves the 12.8% AP on AI-TOD dataset, approaching the performance of the real-valued counterpart.
APA
Xu, S., Wang, M., Li, Y., Lin, M., Zhang, B., Doermann, D. & Sun, X.. (2024). Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:55337-55347 Available from https://proceedings.mlr.press/v235/xu24z.html.

Related Material