Maturity-Gated Anti-Forgetting Sampling for Remote-Sensing Object Detection Training.
Saved in:
| Title: | Maturity-Gated Anti-Forgetting Sampling for Remote-Sensing Object Detection Training. |
|---|---|
| Authors: | Zhou, Yuezheng1 (AUTHOR), Ning, Chenghao1 (AUTHOR), Zhong, Lijun1 (AUTHOR), Zhang, Xiaohu1 (AUTHOR) zhangxiaohu@mail.sysu.edu.cn |
| Source: | Remote Sensing. Aug2026, Vol. 18 Issue 16, p2657. 21p. |
| Subjects: | Remote sensing, Sampling methods, Object recognition (Computer vision), Aerial photography, Machine learning |
| Abstract: | Highlights: What are the main findings? MG-AFSS treats AFSS activation as a detector-maturity decision rather than a fixed warm-up. Validation-history gating gives a more stable accuracy–training-cost trade-off than fixed-activation AFSS. What are the implications of the main findings? The gate can activate early, activate late, or remain inactive across training scenarios. This fallback reduces premature-sampling risk for remote-sensing detector training. Remote-sensing object detection commonly requires repeated training on high-resolution aerial and satellite imagery, where targets may be small, densely distributed, and surrounded by extensive background. For remote-sensing detection tasks that require shorter model-training cycles, reducing training time without sacrificing detection accuracy is important. The Anti-Forgetting Sampling Strategy (AFSS) reduces training time by avoiding repeated processing of learned images, but its fixed warm-up may start sampling before the detector is mature and thereby reduce accuracy. We propose Maturity-Gated AFSS (MG-AFSS), a detector-maturity activation controller for AFSS. The method accumulates validation mean average precision at an intersection-over-union threshold of 0.50 (mAP50), fits a cumulative saturating curve online, and enables AFSS only when the estimated maturity indicates trustworthy image states. After activation, it reuses the original AFSS sampling rule. We evaluate MG-AFSS with matched lightweight detectors on five public remote-sensing datasets: NWPU VHR for the main three-seed study and additional settings; UCAS-AOD for horizontal-box detection; HRSC2016 and ShipRSImageNet for oriented bounding-box (OBB) boundary cases; and DOTAv1 for a larger-scale OBB block. In the three-seed, 80-epoch, from-scratch NWPU VHR experiment, MG-AFSS improves over AFSS by +0.0264 mAP50 and +0.0319 mAP50–95, where mAP50–95 denotes mean average precision averaged over intersection-over-union thresholds from 0.50 to 0.95. It keeps mAP50–95 essentially equal to standard full-dataset training (+0.0003), with a training-time ratio of 0.867 relative to standard training. In a pretrained NWPU setting, the training-time ratio is 0.557 relative to matched standard training, with a higher checkpoint mAP50. In the DOTAv1 block, MG-AFSS has a training-time ratio of 0.759, lower than AFSS at 0.777; its checkpoint-best differences from standard training are −0.0095 mAP50 and −0.0149 mAP50–95, both smaller in magnitude than those of AFSS. Overall, MG-AFSS yields a conditional accuracy–training-time trade-off: it reduces training time when the maturity condition is satisfied and, as observed in the two smaller OBB boundary runs, retains full-dataset training otherwise. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? MG-AFSS treats AFSS activation as a detector-maturity decision rather than a fixed warm-up. Validation-history gating gives a more stable accuracy–training-cost trade-off than fixed-activation AFSS. What are the implications of the main findings? The gate can activate early, activate late, or remain inactive across training scenarios. This fallback reduces premature-sampling risk for remote-sensing detector training. Remote-sensing object detection commonly requires repeated training on high-resolution aerial and satellite imagery, where targets may be small, densely distributed, and surrounded by extensive background. For remote-sensing detection tasks that require shorter model-training cycles, reducing training time without sacrificing detection accuracy is important. The Anti-Forgetting Sampling Strategy (AFSS) reduces training time by avoiding repeated processing of learned images, but its fixed warm-up may start sampling before the detector is mature and thereby reduce accuracy. We propose Maturity-Gated AFSS (MG-AFSS), a detector-maturity activation controller for AFSS. The method accumulates validation mean average precision at an intersection-over-union threshold of 0.50 (mAP50), fits a cumulative saturating curve online, and enables AFSS only when the estimated maturity indicates trustworthy image states. After activation, it reuses the original AFSS sampling rule. We evaluate MG-AFSS with matched lightweight detectors on five public remote-sensing datasets: NWPU VHR for the main three-seed study and additional settings; UCAS-AOD for horizontal-box detection; HRSC2016 and ShipRSImageNet for oriented bounding-box (OBB) boundary cases; and DOTAv1 for a larger-scale OBB block. In the three-seed, 80-epoch, from-scratch NWPU VHR experiment, MG-AFSS improves over AFSS by +0.0264 mAP50 and +0.0319 mAP50–95, where mAP50–95 denotes mean average precision averaged over intersection-over-union thresholds from 0.50 to 0.95. It keeps mAP50–95 essentially equal to standard full-dataset training (+0.0003), with a training-time ratio of 0.867 relative to standard training. In a pretrained NWPU setting, the training-time ratio is 0.557 relative to matched standard training, with a higher checkpoint mAP50. In the DOTAv1 block, MG-AFSS has a training-time ratio of 0.759, lower than AFSS at 0.777; its checkpoint-best differences from standard training are −0.0095 mAP50 and −0.0149 mAP50–95, both smaller in magnitude than those of AFSS. Overall, MG-AFSS yields a conditional accuracy–training-time trade-off: it reduces training time when the maturity condition is satisfied and, as observed in the two smaller OBB boundary runs, retains full-dataset training otherwise. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18162657 |
