Towards Robust Cross-Dataset Object Detection Generalization under Domain Specificity
Object detectors often perform well in-distribution, yet degrade sharply on a different benchmark. We study cross-dataset object detection (CD-OD) through a lens of setting specificity. We group benchmarks into setting-agnostic datasets with diverse everyday scenes and setting-specific datasets tied to a narrow environment, and evaluate a standard detector family across all train--test pairs. This reveals a clear structure in CD-OD: transfer within the same setting type is relatively stable, while transfer across setting types drops substantially and is often asymmetric. The most severe breakdowns occur when transferring from specific sources to agnostic targets, and persist after open-label alignment, indicating that domain shift dominates in the hardest regimes. To disentangle domain shift from label mismatch, we compare closed-label transfer with an open-label protocol that maps predicted classes to the nearest target label using CLIP similarity. Open-label evaluation yields consistent but bounded gains, and many corrected cases correspond to semantic near-misses supported by the image evidence. Overall, we provide a principled characterization of CD-OD under setting specificity and practical guidance for evaluating detectors under distribution shift. Code will be released at \href{[https://github.com/Ritabrata04/cdod-icpr.git}{https://github.com/Ritabrata04/cdod-icpr}.
Code (0)
등록된 구현이 없습니다.
Tasks
Object DetectionSimilar Papers 제목 키워드 기반
Object Detection, Recognition, Deep Learning, and the Universal Law of Generalization
Object detection and recognition are fundamental functions underlying the success of species. Because the appearance of an object exhibits a large variability, the brain has to group these different stimuli under the sam…
Deep LearningObjectobject-detectionObject DetectionMAGneT-3D: Monocular and Domain-Generalizable Temporal 3D Detection
Monocular temporal 3D detection aims to detect objects in 3D, given a monocular video. Query-based 3D detectors unify detection and cross-view association, but their learnable queries fit the spatial distribution of the …
Domain Generalization3D Object DetectionWQT and DG-YOLO: towards domain generalization in underwater object detection
A General Underwater Object Detector (GUOD) should perform well on most of underwater circumstances. However, with limited underwater dataset, conventional object detection methods suffer from domain shift severely. This…
Data AugmentationDiversityDomain GeneralizationObject+2SemSegBench & DetecBench: Benchmarking Reliability and Generalization Beyond Classification
Reliability and generalization in deep learning are predominantly studied in the context of image classification. Yet, real-world applications in safety-critical domains involve a broader set of semantic tasks, such as s…
BenchmarkingClassificationimage-classificationImage Classification+4Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning
Out-of-distribution (OOD) detection and OOD generalization are widely studied in Deep Neural Networks (DNNs), yet their relationship remains poorly understood. We empirically show that the degree of Neural Collapse (NC) …
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionTransfer Learning