• Corpus ID: 140254554

Segmentation is All You Need

  title={Segmentation is All You Need},
  author={Yuxiang Wu and Zehua Cheng and Zhenghua Xu and Weiyan Wang},
Region proposal mechanisms are essential for existing deep learning approaches to object detection in images. Although they can generally achieve a good detection performance under normal circumstances, their recall in a scene with extreme cases is unacceptably low. This is mainly because bounding box annotations contain much environment noise information, and non-maximum suppression (NMS) is required to select target boxes. Therefore, in this paper, we propose the first anchor-free and NMS… 

Figures and Tables from this paper

IPG-Net: Image Pyramid Guidance Network for Object Detection

This paper is the first to introduce an image pyramid guidance sub-network, which supplies spatial information to each scale’s feature to solve the information imbalance problem, and promises even in the deepest stage of the ResNet, there is enough spatial information for bounding box regression and classification.

IPG-Net: Image Pyramid Guidance Network for Small Object Detection

A novel network called Image Pyramid Guidance Network (IPG-Net) is proposed to make sure both the spatial information and semantic information are abundant for each layer to solve the information imbalance problem of Convolutional Neural Network-based object detection.

ZoomInNet: A Novel Small Object Detector in Drone Images with Cross-Scale Knowledge Distillation

Experiments on the challenging Visdrone2018 dataset show that the proposed CSKD method draws on the advantages of the image pyramid methods, while avoids the large calculation of them and significantly improves the detection accuracy of small objects.

Learning Class-Based Graph Representation for Object Detection

A novel graph modeling mechanism with class-based graph representation, which contributes to modeling the high-order topology structure that maps the data distribution to make the detection models have better relational reasoning ability.

Going Deeper Into Face Detection: A Survey

A detailed overview of some of the most representative deep learning based face detection methods by grouping them into a few major categories, and presenting their core architectural designs and accuracies on popular benchmarks is provided.

VisDrone-DET2019: The Vision Meets Drone Object Detection in Image Challenge Results

The goal is to advance the state-of-the-art detection algorithms and provide a comprehensive evaluation platform for them and demonstrate that there still remains a large room for improvement for object detection algorithms on drones.

Vision Meets Drones: Past, Present and Future

The VisDrone dataset, which is captured over various urban/suburban areas of 14 different cities across China from North to South, is described, being the largest such dataset ever published, and enables extensive evaluation and investigation of visual analysis algorithms on the drone platform.

Vehicle Detection From UAV Imagery With Deep Learning: A Review

This article provides a review of the different types of deep learning architectures used to improve vehicle detection from UAV-based images, which could be a useful aid to researchers and developers to select the most adequate method for their needs.

Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies

This survey of autonomous driving technologies with deep learning methods investigates the major fields of self-driving systems, such as perception, mapping and localization, prediction, planning and control, simulation, V2X and safety etc.

Deep Learning in Computer-Aided Diagnosis and Treatment of Tumors: A Survey

According to the specific data types and medical tasks of each stage, the applications of deep learning in the Computer-Aided Diagnosis and Treatment of Tumors and analyzing the excellent works therein are presented.



Simultaneous Detection and Segmentation

This work builds on recent work that uses convolutional neural networks to classify category-independent region proposals (R-CNN), introducing a novel architecture tailored for SDS, and uses category-specific, top-down figure-ground predictions to refine the bottom-up proposals.

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%.

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

  • Jifeng DaiKaiming HeJian Sun
  • Computer Science
    2015 IEEE International Conference on Computer Vision (ICCV)
  • 2015
This paper proposes a method that achieves competitive accuracy but only requires easily obtained bounding box annotations, and yields state-of-the-art results on PASCAL VOC 2012 and PASCal-CONTEXT.

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Expectation-Maximization (EM) methods for semantic image segmentation model training under weakly supervised and semi-supervised settings are developed and extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 image segmentsation benchmark, while requiring significantly less annotation effort.

Instance-Aware Semantic Segmentation via Multi-task Network Cascades

  • Jifeng DaiKaiming HeJian Sun
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
This paper presents Multitask Network Cascades for instance-aware semantic segmentation, which consists of three networks, respectively differentiating instances, estimating masks, and categorizing objects, and develops an algorithm for the nontrivial end-to-end training of this causal, cascaded structure.

Cascade R-CNN: Delving Into High Quality Object Detection

A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset, and experiments show that it is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength.

Soft-NMS — Improving Object Detection with One Line of Code

Soft-NMS is proposed, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M and improves state-of-the-art in object detection from 39.8% to 40.9% with a single model.

FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference

FickleNet explores diverse combinations of locations on feature maps created by generic deep neural networks and implicitly learns the coherence of each location in the feature maps, resulting in a localization map which identifies both discriminative and other parts of objects.

Feature Pyramid Networks for Object Detection

This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.

Microsoft COCO: Common Objects in Context

We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene