Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

Abstract

A recent approach for object detection and human pose estimation is to regress bounding boxes or human keypoints from a central point on the object or person. While this center-point regression is simple and efficient, we argue that the image features extracted at a central point contain limited information for predicting distant keypoints or bounding box boundaries, due to object deformation and scale/orientation variation. To facilitate inference, we propose to instead perform regression from a set of points placed at more advantageous positions. This point set is arranged to reflect a good initialization for the given task, such as modes in the training data for pose estimation, which lie closer to the ground truth than the central point and provide more informative features for regression. As the utility of a point set depends on how well its scale, aspect ratio and rotation matches the target, we adopt the anchor box technique of sampling these transformations to generate additional point-set candidates. We apply this proposed framework, called Point-Set Anchors, to object detection, instance segmentation, and human pose estimation. Our results show that this general-purpose approach can achieve performance competitive with state-of-the-art methods for each of these tasks. Code is available at \url{https://github.com/FangyunWei/PointSetAnchor}

To appear in ECCV 2020

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• Human pose estimation via Convolutional Part Heatmap Regression
• Simple Baselines for Human Pose Estimation and Tracking
• Towards Accurate Multi-person Pose Estimation in the Wild
• Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
• PolarMask: Single Shot Instance Segmentation with Polar Representation
• Self Adversarial Training for Human Pose Estimation
• Single-Stage Multi-Person Pose Machines
• Dense RepPoints: Representing Visual Objects with Dense Point Sets

Cited by in corpus (4)

• RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
• Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
• Prioritized Architecture Sampling with Monto-Carlo Tree Search
• ContourRender: Detecting Arbitrary Contour Shape For Instance Segmentation In One Pass