Breathing New Life Into Small Object Detection With Detection-Oriented Rectification
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-10 · 48 (10) · 13287-13304
DOI: 10.1109/tpami.2026.3704810 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-10. Verfasst von Xiang Yuan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 101 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, Open Fund Project of Xi’an Key Laboratory of Aircraft Optical Imaging and Measurement Technology.
Abstract (Originalsprache)
Small Object Detection (SOD) is fundamentally constrained by the inherent scarcity of visual cues in size-limited instances. This low-entropy nature frequently induces ambiguity and collapse in the learned feature space, critically undermining the efficacy of downstream tasks. Restoration-based methods offer a promising, albeit flawed, solution to this representational bottleneck. On one hand, they excel at recovering fine-grained details; on the other, their effectiveness is compromised by a reliance on synthetic corruptions that generalize poorly at inference, a problem compounded by the inherent conflict between pixel-level fidelity and semantic abstraction. To overcome these limitations, we introduce Detection-Oriented RectificAtion (DORA), a unified framework built upon a novel degradation-then-rectification paradigm. The central insight lies in the principle: knowing what degrades, knowing how to rectify. DORA first explicitly learns to deconstruct complex visual corruptions into a versatile, learnable degradation basis set, providing a structured understanding of the inherent degradation of small instances. This encoded knowledge then forms the dynamic degradation-conditioned prompt, initiating a task-oriented rectification and effectively mitigating the distribution shift at inference. Furthermore, on the foundation of a preceding entity reconstruction task, we devise a synergistic contrastive function to alleviate the task conflict by cyclically aligning rectified entity embeddings with detection-friendly exemplars, thereby robustly bridging the granularity gap between detection and rectification, ultimately facilitating a harmonious optimization of the entire framework. As a paradigm-agnostic solution, DORA can be seamlessly integrated with a wide range of detectors. Comprehensive experiments on five challenging SOD datasets showcase the consistent and substantial performance gains across diverse architectures, underscoring the efficacy and broad potential of our task-oriented rectification strategy.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- Open Fund Project of Xi’an Key Laboratory of Aircraft Optical Imaging and Measurement Technology
Zitieren
APA
Yuan, X., Han, J., & Cheng, G. (2026). Breathing New Life Into Small Object Detection With Detection-Oriented Rectification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(10), 13287-13304. https://doi.org/10.1109/tpami.2026.3704810
Vancouver
Yuan X, Han J, Cheng G. Breathing New Life Into Small Object Detection With Detection-Oriented Rectification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(10):13287-13304. doi:10.1109/tpami.2026.3704810
BibTeX
@article{Yuan2026,
author = {Yuan, Xiang and Han, Junwei and Cheng, Gong},
title = {Breathing New Life Into Small Object Detection With Detection-Oriented Rectification},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {10},
pages = {13287--13304},
doi = {10.1109/tpami.2026.3704810}
}
EUVIMED