Multi-Level Curriculum for Training a Distortion-Aware Barrel Distortion Rectification Model
Barrel distortion rectification aims at removing the radial distortion in a distorted image captured by a wide-angle lens. Previous deep learning methods mainly solve this problem by learning the implicit distortion parameters or the nonlinear rectified mapping function in a direct manner. However, this type of manner results in an indistinct learning process of rectification and thus limits the deep perception of distortion. In this paper, inspired by the curriculum learning, we analyze the barrel distortion rectification task in a progressive and meaningful manner. By considering the relationship among different construction levels in an image, we design a multi-level curriculum that disassembles the rectification task into three levels, structure recovery, semantics embedding, and texture rendering. With the guidance of the curriculum that corresponds to the construction of images, the proposed hierarchical architecture enables a progressive rectification and achieves more accurate results. Moreover, we present a novel distortion-aware pre-training strategy to facilitate the initial learning of neural networks, promoting the model to converge faster and better. Experimental results on the synthesized and real-world distorted image datasets show that the proposed approach significantly outperforms other learning methods, both qualitatively and quantitatively.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
LyriCAR: A Difficulty-Aware Curriculum Reinforcement Learning Framework For Controllable Lyric Translation
Lyric translation is a challenging task that requires balancing multiple musical constraints. Existing methods often rely on hand-crafted rules and sentence-level modeling, which restrict their ability to internalize mus…
Reinforcement LearningConfidence-Aware Paced-Curriculum Learning by Label Smoothing for Surgical Scene Understanding
Curriculum learning and self-paced learning are the training strategies that gradually feed the samples from easy to more complex. They have captivated increasing attention due to their excellent performance in robotic v…
Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONScene UnderstandingSemantic SegmentationGeneric and Trend-aware Curriculum Learning for Relation Extraction
We present a generic and trend-aware curriculum learning approach that effectively integrates textual and structural information in text graphs for relation extraction between entities, which we consider as node pairs in…
RelationRelation ExtractionUnderstanding Curriculum Learning in Large Language Models via Cross-Difficulty Optimization Dynamics
Curriculum learning has been widely adopted in the post-training of large language models by organizing training data from easy to hard. However, its effectiveness varies substantially across reasoning tasks, suggesting …
Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning
Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) trained on a given instruction dataset. Curriculum learning as a typical data organization strategy has shown prelimin…