DCPB: Deformable Convolution Based on the Poincare Ball for Top-view Fisheye Cameras
The accuracy of the visual tasks for top-view fisheye cameras is limited by the Euclidean geometry for pose-distorted objects in images. In this paper, we demonstrate the analogy between the fisheye model and the Poincare ball and that learning the shape of convolution kernels in the Poincare Ball can alleviate the spatial distortion problem. In particular, we propose the Deformable Convolution based on the Poincare Ball, named DCPB, which conducts the Graph Convolutional Network (GCN) in the Poincare ball and calculates the geodesic distances to Poincare hyperplanes as the offsets and modulation scalars of the modulated deformable convolution. Besides, we explore an appropriate network structure in the baseline with the DCPB. The DCPB markedly improves the neural network's performance. Experimental results on the public dataset THEODORE show that DCPB obtains a higher accuracy, and its efficiency demonstrates the potential for using temporal information in fisheye videos.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Poincare ResNet
This paper introduces an end-to-end residual network that operates entirely on the Poincare ball model of hyperbolic space. Hyperbolic learning has recently shown great potential for visual understanding, but is curr…
Deformable Convolution Module with Globally Learned Relative Offsets for Fundus Vessel Segmentation
Deformable convolution can adaptively change the shape of convolution kernel by learning offsets to deal with complex shape features. We propose a novel plug and play deformable convolutional module that uses attention a…
State Space Models for Extractive Summarization in Low Resource Scenarios
Extractive summarization involves selecting the most relevant sentences from a text. Recently, researchers have focused on advancing methods to improve state-of-the-art results in low-resource settings. Motivated by thes…
Extractive SummarizationMambaSentenceState Space ModelsA Novel Bis-Coumarin Targets Multiple Tyrosine Kinases of Key Signaling Pathways in Melanoma and Inhibits Melanoma Cell Survival, Proliferation, and Migration
Melanoma is one of the most dangerous skin malignancies due to its high metastatic tendency and high mortality. Activation of key signaling pathways enforcing melanoma progression depends on phosphorylation of tyrosine k…
Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure
Autonomous agents operating in continuous environments must decide not only what to do, but when to act. We introduce a lightweight adaptive temporal control system that learns the optimal interval between cognitive tick…
Reinforcement Learning