Self-Training for Domain Adaptive Scene Text Detection
원문 초록
Though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the detector in the target domain. However, data collection and annotation are expensive and time-consuming. To address this problem, we propose a self-training framework to automatically mine hard examples with pseudo-labels from unannotated videos or images. To reduce the noise of hard examples, a novel text mining module is implemented based on the fusion of detection and tracking results. Then, an image-to-video generation method is designed for the tasks that videos are unavailable and only images can be used. Experimental results on standard benchmarks, including ICDAR2015, MSRA-TD500, ICDAR2017 MLT, demonstrate the effectiveness of our self-training method. The simple Mask R-CNN adapted with self-training and fine-tuned on real data can achieve comparable or even superior results with the state-of-the-art methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection
GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion
ATI: Any Trajectory Instruction for Controllable Video Generation
Dynamic-I2V: Exploring Image-to-Video Generaion Models via Multimodal LLM
MotionPro: A Precise Motion Controller for Image-to-Video Generation
Hunyuan-Game: Industrial-grade Intelligent Game Creation Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.