Scalable Object Detection using Deep Neural Networks

Abstract

Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012). The winning model on the localization sub-task was a network that predicts a single bounding box and a confidence score for each object category in the image. Such a model captures the whole-image context around the objects but cannot handle multiple instances of the same object in the image without naively replicating the number of outputs for each instance. In this work, we propose a saliency-inspired neural network model for detection, which predicts a set of class-agnostic bounding boxes along with a single score for each box, corresponding to its likelihood of containing any object of interest. The model naturally handles a variable number of instances for each class and allows for cross-class generalization at the highest levels of the network. We are able to obtain competitive recognition performance on VOC2007 and ILSVRC2012, while using only the top few predicted locations in each image and a small number of neural network evaluations.

Cited by in corpus (17)

• Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
• A Review of Object Detection Models based on Convolutional Neural Network
• End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning
• DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
• Single-Shot Refinement Neural Network for Object Detection
• Proposal-free Network for Instance-level Object Segmentation
• DenseCap: Fully Convolutional Localization Networks for Dense Captioning
• PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• End-to-end Learning of Action Detection from Frame Glimpses in Videos
• S${}^3$FD: Single Shot Scale-invariant Face Detector
• DeepBox: Learning Objectness with Convolutional Networks
• Computational Baby Learning
• EdgeNet: Balancing Accuracy and Performance for Edge-based Convolutional Neural Network Object Detectors
• Learning to detect and localize many objects from few examples
• Beyond Pixels: A Comprehensive Survey from Bottom-up to Semantic Image Segmentation and Cosegmentation
• Active Object Localization with Deep Reinforcement Learning