FCOS: A simple and strong anchor-free object detector

@article{Tian2020FCOSAS,
  title={FCOS: A simple and strong anchor-free object detector},
  author={Zhi Tian and Chunhua Shen and Hao Chen and Tong He},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  year={2020},
  volume={PP}
}
  • Zhi Tian, Chunhua Shen, +1 author Tong He
  • Published 14 June 2020
  • Computer Science, Medicine
  • IEEE transactions on pattern analysis and machine intelligence
In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications. Recently one-stage methods have gained much attention over two-stage approaches due to their simpler design and competitive performance. Here we propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to other dense prediction problems such as semantic… Expand
Object Detection Made Simpler by Eliminating Heuristic NMS
We show a simple NMS-free, end-to-end object detection framework, of which the network is a minimal modification to a one-stage object detector such as the FCOS detection model [24]. We attain on parExpand
Unknown Object Segmentation from Stereo Images
TLDR
This work proposes a novel object instance segmentation approach that does not require any semantic or geometric information of the objects beforehand before it is computed, and employs a transformer-based architecture that maps directly from the pair of input images to the object instances. Expand
VinVL: Making Visual Representations Matter in Vision-Language Models
TLDR
This paper develops an improved object detection model to provide object-centric representations of images and feeds the visual features generated into a Transformer-based VL fusion model OSCAR, and utilizes an improved approach OSCARS to pre-train the VL model and fine-tune it on a wide range of downstream VL tasks. Expand
Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy
TLDR
This work proposes a two-task tracking framework (named DMTrack), which utilizes two core components to achieve distractor-aware fast tracking via Dynamic convolutions (d-convs) and Multiple object tracking (MOT) philosophy, and constructs a lightweight one-shot detector using a novel dynamic convolutions generation method. Expand
Revisiting the Loss Weight Adjustment in Object Detection
TLDR
An Adaptive Loss Weight Adjustment (ALWA) is proposed to solve the above two problems by dynamically adjusting the loss weight in the training process, according to statistical characteristics of loss values. Expand
Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild
TLDR
A progressive method that gradually increases the network depth during the search stage, which leads to the Progressive DARTS (P-DARTS) algorithm, which achieves improved performance on both the proxy dataset (CIFAR10) and a few target problems. Expand
Vehicle Detection in Congested Traffic Based on Simplified Weighted Dual-Path Feature Pyramid Network With Guided Anchoring
TLDR
Compared experiments on UA-DETRAC dataset and handcrafted Vehicles of Traffic dataset are conducted to demonstrate the superiority of the proposed Simplified Weighted Dual-path Network with Guided Anchoring framework over other state-of-the-art methods. Expand
Probabilistic two-stage detection
TLDR
A probabilistic interpretation of twostage object detection is developed that motivates a number of common empirical training practices and suggests changes to two-stage detection pipelines. Expand
Regularized Densely-Connected Pyramid Network for Salient Instance Segmentation
TLDR
A new pipeline for end-to-end salient instance segmentation (SIS) that predicts a class-agnostic mask for each detected salient instance, and the regularized dense connections, which attentively promote informative features and suppress non-informative ones from all feature pyramids are proposed. Expand
onMultiscene Vehicle Dataset Based on Improved FCOS Detection Algorithms
  • Fei Yan, Hui Zhang, Tianyang Zhou, Zhiyong Fan, Jia Liu
  • 2021
Whether in intelligent transportation or autonomous driving, vehicle detection is an important part. Vehicle detection still faces many problems, such as inaccurate vehicle detection positioning andExpand
...
1
2
3
...

References

SHOWING 1-10 OF 64 REFERENCES
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
UnitBox: An Advanced Object Detection Network
TLDR
A novel Intersection over Union (IoU) loss function for bounding box prediction, which regresses the four bounds of a predicted box as a whole unit, and introduces the UnitBox, which performs accurate and efficient localization, shows robust to objects of varied shapes and scales, and converges fast. Expand
BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
TLDR
The proposed BlendMask can effectively predict dense per-pixel position-sensitive instance features with very few channels, and learn attention maps for each instance with merely one convolution layer, thus being fast in inference. Expand
CenterMask: Real-Time Anchor-Free Instance Segmentation
We propose a simple yet efficient anchor-free instance segmentation, called CenterMask, that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one stage object detectorExpand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
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. Expand
Focal Loss for Dense Object Detection
TLDR
This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. Expand
CenterNet: Keypoint Triplets for Object Detection
TLDR
This paper presents an efficient solution that explores the visual patterns within individual cropped regions with minimal costs, and builds the framework upon a representative one-stage keypoint-based detector named CornerNet, which improves both precision and recall. Expand
Feature Pyramid Networks for Object Detection
TLDR
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. Expand
DenseBox: Unifying Landmark Localization with End to End Object Detection
TLDR
DenseBox is introduced, a unified end-to-end FCN framework that directly predicts bounding boxes and object class confidences through all locations and scales of an image and shows that when incorporating with landmark localization during multi-task learning, DenseBox further improves object detection accuray. Expand
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
...
1
2
3
4
5
...