Region Proposal by Guided Anchoring

Abstract

Region anchors are the cornerstone of modern object detection techniques. State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios. In this paper, we revisit this foundational stage. Our study shows that it can be done much more effectively and efficiently. Specifically, we present an alternative scheme, named Guided Anchoring, which leverages semantic features to guide the anchoring. The proposed method jointly predicts the locations where the center of objects of interest are likely to exist as well as the scales and aspect ratios at different locations. On top of predicted anchor shapes, we mitigate the feature inconsistency with a feature adaption module. We also study the use of high-quality proposals to improve detection performance. The anchoring scheme can be seamlessly integrated into proposal methods and detectors. With Guided Anchoring, we achieve 9.1% higher recall on MS COCO with 90% fewer anchors than the RPN baseline. We also adopt Guided Anchoring in Fast R-CNN, Faster R-CNN and RetinaNet, respectively improving the detection mAP by 2.2%, 2.7% and 1.2%. Code will be available at https://github.com/open-mmlab/mmdetection.

CVPR 2019 camera ready

References in corpus (8)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• DenseBox: Unifying Landmark Localization with End to End Object Detection
• YOLO9000: Better, Faster, Stronger
• Single-Shot Refinement Neural Network for Object Detection
• Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade
• Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
• Cascade Region Proposal and Global Context for Deep Object Detection

Cited by in corpus (27)

• A Survey of Deep Learning-based Object Detection
• Learning Spatial Fusion for Single-Shot Object Detection
• DetNAS: Backbone Search for Object Detection
• Probabilistic two-stage detection
• Revisiting Feature Alignment for One-stage Object Detection
• Prime Sample Attention in Object Detection
• RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection
• Anchor Box Optimization for Object Detection
• AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy
• Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation
• Learning from Noisy Anchors for One-stage Object Detection
• Localization Distillation for Dense Object Detection
• Learning a Unified Sample Weighting Network for Object Detection
• Reducing Label Noise in Anchor-Free Object Detection
• 2nd Place Solution in Google AI Open Images Object Detection Track 2019
• Augmenting Proposals by the Detector Itself
• Resisting Crowd Occlusion and Hard Negatives for Pedestrian Detection in the Wild
• Instance Scale Normalization for image understanding
• Semi-Anchored Detector for One-Stage Object Detection
• Self-Supervised Scene De-occlusion
• Perceiving Traffic from Aerial Images
• Working with scale: 2nd place solution to Product Detection in Densely Packed Scenes [Technical Report]
• Semi-supervised Learning for Dense Object Detection in Retail Scenes
• Bootstrap Your Object Detector via Mixed Training
• PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection