Miss Detection vs. False Alarm: Adversarial Learning for Small Object Segmentation in Infrared Images

By Huan Wang, Luping Zhou, Lei Wang. IEEE International Conference on Computer Vision, 2019

430 citations recorded by the source corpus.

A key challenge of infrared small object segmentation (ISOS) is to balance miss detection (MD) and false alarm (FA). This usually needs ``opposite'' strategies to suppress the two terms, and has not been well resolved in the literature. In this paper, we propose a deep adversarial learning framework to improve this situation. Departing from the tradition of jointly reducing MD and FA via a single objective, we decompose this difficult task into two sub-tasks handled by two models trained adversarially, with each focusing on reducing either MD or FA. Such a new design brings forth at least three advantages. First, as each model focuses on a relatively simpler sub-task, the overall difficulty of ISOS is somehow decreased. Second, the adversarial training of the two models naturally produces a delicate balance of MD and FA, and low rates for both MD and FA could be achieved at Nash equilibrium. Third, this MD-FA detachment gives us more flexibility to develop specific models dedicated to each sub-task. To realize the above design, we propose a conditional Generative Adversarial Network comprising of two generators and one discriminator. Each generator strives for one sub-task, while the discriminator differentiates the three segmentation results from the two generators and the ground truth. Moreover, in order to better serve the sub-tasks, the two generators, based on context aggregation networks, utilzse different size of receptive fields, providing both local and global views of objects for segmentation. As verified on multiple infrared image data sets, our method consistently achieves better segmentation than many state-of-the-art ISOS methods.

Subfields: Aerospace Engineering, Biophysics, Media Technology

View Paper: https://www.semanticscholar.org/paper/371c0c05ca0d66027a7b79dde45ab2f953cf67ba

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Zhenming Peng
2. Jocelyn Chanussot
3. Danfeng Hong
4. Xin Wu
5. Kobus Barnard
6. Fei Zhou
7. Wei An
8. Siying Cao

In Biophysics

1. Kobus Barnard
2. Jocelyn Chanussot
3. Fei Zhou
4. Yimian Dai
5. Zhenming Peng
6. Yiquan Wu

In Media Technology

1. Danfeng Hong
2. Jocelyn Chanussot
3. Xin Wu
4. Kobus Barnard
5. Yulan Guo
6. Fei Zhou
7. Longguang Wang
8. Yimian Dai

Citations in the corpus

• Dense Nested Attention Network for Infrared Small Target Detection (2021, methodology): “For CNN-based methods, we followed their original papers and adopted their fixed thresholds (i.e., 0, 0, 0.5 for ACM [24], ALCNet [31], and MDvsFA-cGAN [32], respectively).”
• UIU-Net: U-Net in U-Net for Infrared Small Object Detection (2022, background): “2) Synthetic Infrared Small Target Detection Data [45]: The synthetic dataset3 is a large open and synthetic singleframe infrared small object detection dataset.”
• Asymmetric Contextual Modulation for Infrared Small Target Detection (2020, background): “Most algorithms are evaluated on private datasets consisting of very limited images [31], which is easy to make the performance comparison unfair and inaccurate.”
• Attention-Guided Pyramid Context Networks for Detecting Infrared Small Target Under Complex Background (2023, methodology): “Data-driven approaches combining neural networks and public datasets [19], [20] can automatically extract features to detect targets.”
• ISNet: Shape Matters for Infrared Small Target Detection (2022, methodology): “Then, Wang et al. [34] proposed MDvsFA for SIRSTD, which achieved a trade-off between false alarm and miss detection.”