CentripetalText: An Efficient Text Instance Representation for Scene Text Detection
Dec 6, 2021
Speakers
About
Scene text detection remains a grand challenge due to the variation in text curvatures, orientations, and aspect ratios. One of the most intractable problems is how to represent text instances of arbitrary shapes. Although many state-of-the-art methods have been proposed to model irregular texts in a flexible manner, most of them lose simplicity and robustness. Their complicated post-processings and the regression under Dirac delta distribution undermine the detection performance and the generalization ability. In this paper, we propose an efficient text instance representation named CentripetalText (CT), which decomposes text instances into the combination of text kernels and centripetal shifts. Specifically, we utilize the centripetal shifts to implement the pixel aggregation, which guide the external text pixels to the internal text kernels. The relaxation operation is integrated into the dense regression for centripetal shifts, allowing the correct prediction in a range, not a specific value. The convenient reconstruction of the text contours and the tolerance of the prediction errors in our method guarantee the high detection accuracy and the fast inference speed respectively. Besides, we shrink our text detector into a proposal generation module, namely CentripetalText Proposal Network (CPN), replacing SPN in Mask TextSpotter v3 and producing more accurate proposals. To validate the effectiveness of our designs, we conduct experiments on several commonly used scene text benchmarks, including both curved and multi-oriented text datasets. For the task of scene text detection, our approach achieves superior or competitive performance compared to other existing methods, e.g., F-measure of 86.3Scene text detection remains a grand challenge due to the variation in text curvatures, orientations, and aspect ratios. One of the most intractable problems is how to represent text instances of arbitrary shapes. Although many state-of-the-art methods have been proposed to model irregular texts in a flexible manner, most of them lose simplicity and robustness. Their complicated post-processings and the regression under Dirac delta distribution undermine the detection performance and the general…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Unadversarial Examples: Designing Objects for Robust Vision
Watch later
Hadi Salman, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Combining Recurrent, Convolutional, and Continuous-time Models with the Linear State Space Layer
Watch later
Albert Gu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Semantic Code Classification for Automated Machine Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Playful Interactions for Representation Learning
Watch later
Sarah Young, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
eXplainable AI approaches for debugging and diagnosis
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Panel Discussion 2
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%