TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation
The research focus of scene text detection and recognition has shifted to arbitrary shape text in recent years, where the text shape representation is a fundamental problem. An ideal representation should be compact, complete, efficient, and reusable for subsequent recognition in our opinion. However, previous representations have flaws in one or more aspects. Thin-Plate-Spline (TPS) transformation has achieved great success in scene text recognition. Inspired by this, we reversely think of its usage and sophisticatedly take TPS as an exquisite representation for arbitrary shape text representation. The TPS representation is compact, complete, and efficient. With the predicted TPS parameters, the detected text region can be directly rectified to a near-horizontal one to assist the subsequent recognition. To further exploit the potential of the TPS representation, the Border Alignment Loss is proposed. Based on these designs, we implement the text detector TPSNet, which can be extended to a text spotter conveniently. Extensive evaluation and ablation of several public benchmarks demonstrate the effectiveness and superiority of the proposed method for text representation and spotting. Particularly, TPSNet achieves the detection F-Measure improvement of 4.4\% (78.4\% vs. 74.0\%) on Art dataset and the end-to-end spotting F-Measure improvement of 5.0\% (78.5\% vs. 73.5\%) on Total-Text, which are large margins with no bells and whistles.
Code (1)
Tasks
Scene Text DetectionScene Text RecognitionText DetectionText SpottingSimilar Papers 제목 키워드 기반
GRP: Goal-Reversed Prompting for Zero-Shot Evaluation with LLMs
Using Large Language Models (LLMs) to evaluate and compare two answers from different models typically involves having LLM-based judges select the better answer. However, humans often approach problem-solving from a reve…
Decision MakingModeling reverse thinking for machine learning
Human inertial thinking schemes can be formed through learning, which are then applied to quickly solve similar problems later. However, when problems are significantly different, inertial thinking generally presents the…
BIG-bench Machine LearningAuditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries
Evaluations of unlearning on reasoning models sometimes show a bypass pattern. The answer side looks unlearned, but the model's own thinking trace keeps emitting the forgotten content, and the gap is taken as evidence th…
Reworking geometric morphometrics into a methodology of transformation grids
Today's typical application of geometric morphometrics to a quantitative comparison of organismal anatomies begins by standardizing samples of homologously labelled point configurations for location, orientation, and sca…
Reverse Thinking Makes LLMs Stronger Reasoners
Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances ove…
Data AugmentationKnowledge DistillationLogical ReasoningMath+1