Improving object detection with region similarity learning

  title={Improving object detection with region similarity learning},
  author={Feng Gao and Yihang Lou and Yan Bai and Shiqi Wang and Tiejun Huang and Ling-yu Duan},
  journal={2017 IEEE International Conference on Multimedia and Expo (ICME)},
  • F. GaoYihang Lou Ling-yu Duan
  • Published 1 March 2017
  • Computer Science
  • 2017 IEEE International Conference on Multimedia and Expo (ICME)
Object detection aims to identify instances of semantic objects of a certain class in images or videos. The success of state-of-the-art approaches is attributed to the significant progress of object proposal and convolutional neural networks (CNNs). Most promising detectors involve multi-task learning with an optimization objective of softmax loss and regression loss. The first is for multi-class categorization, while the latter is for improving localization accuracy. However, few of them… 

Figures and Tables from this paper

Interpretation of intelligence in CNN-pooling processes: a methodological survey

The state of the art on selection of global feature for pooling process mainly based on four categories such as value, probability, rank and transformed domain is presented.

An Interpretable Deep Architecture for Similarity Learning Built Upon Hierarchical Concepts

An effective similarity neural network (SNN) is proposed not only to seek robust retrieval performance but also to achieve satisfactory post-hoc interpretability, and can offer superior performance when compared against state-of-the-art approaches.



Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.

Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model

An object detection system that relies on a multi-region deep convolutional neural network that also encodes semantic segmentation-aware features that aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization.

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.

Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction

This work addresses the localization problem by using a search algorithm based on Bayesian optimization that sequentially proposes candidate regions for an object bounding box, and training the CNN with a structured loss that explicitly penalizes the localization inaccuracy.

SSD: Single Shot MultiBox Detector

The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.

Training Region-Based Object Detectors with Online Hard Example Mining

OHEM is a simple and intuitive algorithm that eliminates several heuristics and hyperparameters in common use that leads to consistent and significant boosts in detection performance on benchmarks like PASCAL VOC 2007 and 2012.

Object Detection with Discriminatively Trained Part Based Models

We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in

Contextualizing Object Detection and Classification

This paper adopts a new method for adaptive context modeling and iterative boosting that achieves the state-of-the-art performance on object classification and detection tasks of PASCAL Visual Object Classes Challenge (VOC) 2007, 2010 and SUN09 data sets.

Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks

The Inside-Outside Net (ION), an object detector that exploits information both inside and outside the region of interest, provides strong evidence that context and multi-scale representations improve small object detection.

Scale-Aware Fast R-CNN for Pedestrian Detection

This paper argues that the issue of large variance in instance scales, which results in undesirable large intracategory variance in features, may severely hurt the performance of modern object instance detection methods, can be substantially alleviated by the divide-and-conquer philosophy.