CD-FSOD: A Benchmark For Cross-Domain Few-Shot Object Detection
Wuti Xiong
Abstract
In this paper, we propose a study of the cross-domain few-shot object detection (CD-FSOD) benchmark, consisting of image data from a diverse data domain. On the proposed benchmark, we evaluate state-of-art FSOD approaches, including meta-learning FSOD approaches and fine-tuning FSOD approaches. The results show that these methods tend to fall, and even underperform the naive fine-tuning model. We analyze the reasons for their failure and introduce a strong baseline that uses a mutually-beneficial manner to alleviate the overfitting problem. Our approach is remarkably superior to existing approaches by significant margins (2.0% on average) on the proposed benchmark. Our code is available at https://github.com/FSOD/CD-FSOD.
Topics & Concepts
Benchmark (surveying)OverfittingComputer scienceDomain (mathematical analysis)Artificial intelligenceCode (set theory)Object detectionObject (grammar)Machine learningSource codePattern recognition (psychology)Data miningArtificial neural networkMathematicsOperating systemSet (abstract data type)Programming languageGeographyMathematical analysisGeodesyDomain Adaptation and Few-Shot LearningAdvanced Neural Network ApplicationsMultimodal Machine Learning Applications