What makes for effective detection proposals?

2015-02-17 · Jan Hosang, Rodrigo Benenson, Piotr Dollár, Bernt Schiele

Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in-depth analysis of twelve proposal methods along with four baselines regarding proposal repeatability, ground truth annotation recall on PASCAL, ImageNet, and MS COCO, and their impact on DPM, R-CNN, and Fast R-CNN detection performance. Our analysis shows that for object detection improving proposal localisation accuracy is as important as improving recall. We introduce a novel metric, the average recall (AR), which rewards both high recall and good localisation and correlates surprisingly well with detection performance. Our findings show common strengths and weaknesses of existing methods, and provide insights and metrics for selecting and tuning proposal methods.

📄 PDF Abstract BibTeX arXiv:1502.05082

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detection Object Detection

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

RoIPool 설명 없음

Fast R-CNN Fast R-CNN is an object detection model that improves in its predecessor R-CNN in a number of ways. Instead of extracting CNN…

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

R-CNN R-CNN, or Regions with CNN Features, is an object detection model that uses high-capacity CNNs to bottom-up region proposals in order to localize and segment objects. It…

Delving into the Imbalance of Positive Proposals in Two-stage Object Detection

2020-05-23 · Zheng Ge, Zequn Jie, Xin Huang, Chengzheng Li 외

Imbalance issue is a major yet unsolved bottleneck for the current object detection models. In this work, we observe two crucial yet never discussed imbalance issues. The first imbalance lies in the large number of low-q…

object-detection Object Detection

You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection

2019-06-01 · CVPR 2019 6 · Krishna Kumar Singh, Yong Jae Lee

We propose a novel way of using videos to obtain high precision object proposals for weakly-supervised object detection. Existing weakly-supervised detection approaches use off-the-shelf proposal methods like edge boxes…

Object object-detection Object Detection Region Proposal+1

What leads to generalization of object proposals?

2020-08-13 · Rui Wang, Dhruv Mahajan, Vignesh Ramanathan

Object proposal generation is often the first step in many detection models. It is lucrative to train a good proposal model, that generalizes to unseen classes. This could help scaling detection models to larger number o…

Diversity Object Object Proposal Generation

Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection

2022-10-05 · Khurram Azeem Hashmi, Didier Stricker, Muhammamd Zeshan Afzal

This paper presents the novel idea of generating object proposals by leveraging temporal information for video object detection. The feature aggregation in modern region-based video object detectors heavily relies on lea…

Object object-detection Object Detection Video Object Detection

Who Should Review Your Proposal? Interdisciplinary Topic Path Detection for Research Proposals

2022-03-07 · Meng Xiao, Ziyue Qiao, Yanjie Fu, Hao Dong 외

The peer merit review of research proposals has been the major mechanism to decide grant awards. Nowadays, research proposals have become increasingly interdisciplinary. It has been a longstanding challenge to assign pro…