Adaptive Object Detection Using Adjacency and Zoom Prediction

2015/12/24 by Yongxi Lu, Lu, Yongxi, Tara Javidi +3 · 2 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Visual Attention and Saliency Detection

paper · pdf · doi:10.48550/arxiv.1512.07711

openalex publication_date 2015/12/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are computationally efficient, they rely on fixed image regions as anchors for predictions. In this paper we propose to use a search strategy that adaptively directs computational resources to sub-regions likely to contain objects. Compared to methods based on fixed anchor locations, our approach naturally adapts to cases where object instances are sparse and small. Our approach is comparable in terms of accuracy to the state-of-the-art Faster R-CNN approach while using two orders of magnitude fewer anchors on average. Code is publicly available.

Citations

• Computational Baby Learning
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ImageNet classification with deep convolutional neural networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks

Cited by

• Dynamic Zoom-in Network for Fast Object Detection in Large Images
• Active Object Localization in Visual Situations

Related

• Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features
• An active search strategy for efficient object class detection
• Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters
• R-CNN minus R
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks