I$^2$OL-Net: Intra-Inter Objectness Learning Network for Point-Supervised X-Ray Prohibited Item Detection
Abstract
Automatic detection of prohibited items in X-ray images plays a crucial role in public security. However, existing methods rely heavily on labor-intensive box annotations. To address this, we investigate X-ray prohibited item detection under labor-efficient point supervision and develop an intra-inter objectness learning network (IOL-Net). IOL-Net consists of two key modules: an intra-modality objectness learning (intra-OL) module and an inter-modality objectness learning (inter-OL) module. The intra-OL module designs a local focus Gaussian masking block and a global random Gaussian masking block to collaboratively learn the objectness in X-ray images. Meanwhile, the inter-OL module introduces the wavelet decomposition-based adversarial learning block and the objectness block, effectively reducing the modality discrepancy and transferring the objectness knowledge learned from natural images with box annotations to X-ray images. Based on the above, IOL-Net greatly alleviates the problem of part domination caused by severe intra-class variations in X-ray images. Experimental results on four X-ray datasets show that IOL-Net can achieve superior performance with a significant reduction of annotation cost, thus enhancing its accessibility and practicality.
Keywords
Cite
@article{arxiv.2412.03811,
title = {I$^2$OL-Net: Intra-Inter Objectness Learning Network for Point-Supervised X-Ray Prohibited Item Detection},
author = {Sanjoeng Wong and Yan Yan},
journal= {arXiv preprint arXiv:2412.03811},
year = {2025}
}
Comments
We identified technical errors during a subsequent review of our paper, which may impact the accuracy of the conclusions. For instance, Table 1 did not adequately account for the fact that P2BNet was not trained on the COCO dataset, which could lead to results that do not fully reflect the actual performance of the method