Corpus ID: 218901074

Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3

@article{Hurtk2020PolyYOLOHS,
  title={Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3},
  author={Petr Hurt{\'i}k and Vojtech Molek and Jan Hula and Marek Vajgl and Pavel Vlas{\'a}nek and Tomas Nejezchleba},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.13243}
}
We present a new version of YOLO with better performance and extended with instance segmentation called Poly-YOLO. Poly-YOLO builds on the original ideas of YOLOv3 and removes two of its weaknesses: a large amount of rewritten labels and inefficient distribution of anchors. Poly-YOLO reduces the issues by aggregating features from a light SE-Darknet-53 backbone with a hypercolumn technique, using stairstep upsampling, and produces a single scale output with high resolution. In comparison with… Expand
Smart-YOLO: A Light-Weight Real-time Object Detection Network
TLDR
This work proposes a new lightweight algorithm Smart-YOLO based on the YOLO framework which uses inverted bottleneck blocks and deep-wise separable convolution, and puts forward a new loss function to make up for the loss of accuracy caused by the replacement of the backbone network. Expand
U2-ONet: A Two-level Nested Octave U-structure with Multiscale Attention Mechanism for Moving Instances Segmentation
TLDR
This work proposes a two-level nested Octave U-structure network with a multiscale attention mechanism called U2-ONet, and introduces a hierarchical training supervision strategy that calculates the loss at each level while adding a knowledge matching loss to keep the optimization consistency. Expand
CenterPoly: real-time instance segmentation using bounding polygons
TLDR
A novel method for realtime instance segmentation using bounding polygons to detect road users in dense urban environments, making it suitable for applications in intelligent transportation systems like automated vehicles. Expand
U2-ONet: A Two-Level Nested Octave U-Structure Network with a Multi-Scale Attention Mechanism for Moving Object Segmentation
TLDR
A two-level nested octave U-structure network with a multi-scale attention mechanism, called U2-ONet, that can achieve a state-of-the-art performance in several general moving object segmentation datasets. Expand
YOLOv3: Face Detection in Complex Environments
TLDR
Experimental results show that after adjustment, the YOLOv3 model has more advantages in face detection than the original model in complex environments. Expand
Real-time detector design for small targets based on bi-channel feature fusion mechanism
TLDR
A real-time detector with a bi-channel feature fusion mechanism is proposed based on YOLOv4-tiny, called BFF-YOLO, which effectively improves the detection of small targets and occluded objects. Expand
Feature Selection Module for CNN Based Object Detector
TLDR
A new feature fusion module called the Feature Selection Module (FSM) was proposed in this paper, which can automatically detect the most representative features for the rebuilding of feature maps and is able to consistently improve the performance of Yolo detectors. Expand
Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline
TLDR
This work designs a novel curved bounding box model that has optimal properties for fisheye distortion models and designs a curvature adaptive perimeter sampling method for obtaining polygon vertices, improving relative mAP score by 4.9% compared to uniform sampling. Expand
Real-Time Target Detection in Visual Sensing Environments Using Deep Transfer Learning and Improved Anchor Box Generation
TLDR
This paper proposes a deep transfer learning strategy for real-time target detection for situations where acquiring large-scale data is complicated and challenging, and examines the sustainable outperformance in three typical applications, digital pathology, smart agriculture and remote sensing, in vision-based sensing environments. Expand
FisheyeYOLO: Object Detection on Fisheye Cameras for Autonomous Driving
In this paper, we tackle Object Detection in fisheye images and study different object representations. The standard bounding box fails in fisheye cameras due to the strong radial distortion,Expand
...
1
2
...

References

SHOWING 1-10 OF 41 REFERENCES
YOLO-ASC: You Only Look Once And See Contours
TLDR
This work proposes YOLO-ASC, which, for rectangular-based objects, detects bounding boxes together with object contour using a quadrangular, and presents two experiments where it is demonstrated that YOLo-ASC training converges faster due to the symbiosis between the bounding box detection and quadr angular detection. Expand
YOLO9000: Better, Faster, Stronger
TLDR
YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories, is introduced and a method to jointly train on object detection and classification is proposed, both novel and drawn from prior work. Expand
PolarMask: Single Shot Instance Segmentation With Polar Representation
  • Enze Xie, Pei Sun, +5 authors Ping Luo
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used by easily embedding it into mostExpand
Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns
TLDR
Using hypercolumns as pixel descriptors, CNN recognition algorithms based on convolutional networks show results on three fine-grained localization tasks: simultaneous detection and segmentation, keypoint localization, and part labeling. Expand
SOLOv2: Dynamic, Faster and Stronger
TLDR
State-of-the-art results in object detection (from the authors' mask byproduct) and panoptic segmentation show the potential to serve as a new strong baseline for many instance-level recognition tasks besides instance segmentation. Expand
YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers
This paper focuses on YOLO-LITE, a real-time object detection model developed to run on portable devices such as a laptop or cellphone lacking a Graphics Processing Unit (GPU). The model was firstExpand
You Only Look Once: Unified, Real-Time Object Detection
TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork. Expand
YOLOv3: An Incremental Improvement
We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but moreExpand
FCOS: Fully Convolutional One-Stage Object Detection
TLDR
For the first time, a much simpler and flexible detection framework achieving improved detection accuracy is demonstrated, and it is hoped that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Expand
SSD: Single Shot MultiBox Detector
TLDR
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. Expand
...
1
2
3
4
5
...