paper-with-me

Papers

CornerNet-Lite: Efficient Keypoint Based Object Detection

2019-04-18 · Hei Law, Yun Teng, Olga Russakovsky, Jia Deng

Keypoint-based methods are a relatively new paradigm in object detection, eliminating the need for anchor boxes and offering a simplified detection framework. Keypoint-based CornerNet achieves state of the art accuracy among single-stage detectors. However, this accuracy comes at high processing cost. In this work, we tackle the problem of efficient keypoint-based object detection and introduce CornerNet-Lite. CornerNet-Lite is a combination of two efficient variants of CornerNet: CornerNet-Saccade, which uses an attention mechanism to eliminate the need for exhaustively processing all pixels of the image, and CornerNet-Squeeze, which introduces a new compact backbone architecture. Together these two variants address the two critical use cases in efficient object detection: improving efficiency without sacrificing accuracy, and improving accuracy at real-time efficiency. CornerNet-Saccade is suitable for offline processing, improving the efficiency of CornerNet by 6.0x and the AP by 1.0% on COCO. CornerNet-Squeeze is suitable for real-time detection, improving both the efficiency and accuracy of the popular real-time detector YOLOv3 (34.4% AP at 30ms for CornerNet-Squeeze compared to 33.0% AP at 39ms for YOLOv3 on COCO). Together these contributions for the first time reveal the potential of keypoint-based detection to be useful for applications requiring processing efficiency.

📄 PDF Abstract BibTeX arXiv:1904.08900

Code (6)

princeton-vl/CornerNet-Lite 공식 구현 pytorch
Arno3165229/CornerNet_Traffic_Light pytorch
PaddlePaddle/PaddleDetection paddle
hollyprince/ObjectsDetection-CornerNet-Lite pytorch
jason-su/UCGNet pytorch
takooctopus/CornerNet-Lite-Tako pytorch

Tasks

Objectobject-detectionObject DetectionReal-Time Object Detection

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Residual Connection 설명 없음
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…
Hourglass Module 설명 없음
Corner Pooling 설명 없음
Stacked Hourglass Network Stacked Hourglass Networks are a type of convolutional neural network for pose estimation. They are based on the successive steps of pooling and upsampling that are done to…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution

Similar Papers 제목 키워드 기반

CornerNet: Detecting Objects as Paired Keypoints

2018-08-03 · ECCV 2018 9 · Hei Law, Jia Deng

We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detec…

Objectobject-detectionObject Detection

CenterNet: Keypoint Triplets for Object Detection

2019-04-17 · ICCV 2019 10 · Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi 외

In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions. This paper presents an efficient sol…

Objectobject-detectionObject DetectionTriplet

Lite-FPN for Keypoint-based Monocular 3D Object Detection

2021-05-01 · Lei Yang, Xinyu Zhang, Li Wang, Minghan Zhu 외

3D object detection with a single image is an essential and challenging task for autonomous driving. Recently, keypoint-based monocular 3D object detection has made tremendous progress and achieved great speed-accuracy t…

3D Object DetectionAutonomous DrivingMonocular 3D Object DetectionObject+2

CoKe: Localized Contrastive Learning for Robust Keypoint Detection

2020-09-29 · Yutong Bai, Angtian Wang, Adam Kortylewski, Alan Yuille

In this paper, we introduce a contrastive learning framework for keypoint detection (CoKe). Keypoint detection differs from other visual tasks where contrastive learning has been applied because the input is a set of ima…

Contrastive LearningKeypoint DetectionRepresentation Learning

TetraPackNet: Four-Corner-Based Object Detection in Logistics Use-Cases

2021-04-19 · Laura Dörr, Felix Brandt, Alexander Naumann, Martin Pouls

While common image object detection tasks focus on bounding boxes or segmentation masks as object representations, we consider the problem of finding objects based on four arbitrary vertices. We propose a novel model, na…

Objectobject-detectionObject Detection