MegDet: A Large Mini-Batch Object Detector

Recent CNN based object detectors, no matter one-stage methods like YOLO [1,2], SSD [3], and RetinaNet [4] or two-stage detectors like Faster R-CNN [5], R-FCN [6] and FPN [7] are usually trying to directly finetune from ImageNet pre-trained models designed for image classification. There has been little work discussing on the backbone feature extractor specifically designed for the object detection. More importantly, there are several differences between the tasks of image classification and object detection. (i) Recent object detectors like FPN and RetinaNet usually involve extra stages against the task of image classification to handle the objects with various scales. (ii) Object detection not only needs to recognize the category of the object instances but also spatially locate the position. Large downsampling factor brings large valid receptive field, which is good for image classification but compromises the object location ability. Due to the gap between the image classification and object detection, we propose DetNet in this paper, which is a novel backbone network specifically designed for object detection. Moreover, DetNet includes the extra stages against traditional backbone network for image classification, while maintains high spatial resolution in deeper layers. Without any bells and whistles, state-of-the-art results have been obtained for both object detection and instance segmentation on the MSCOCO benchmark based on our DetNet (4.8G FLOPs) backbone. The code will be released for the reproduction.

show abstract

“…The results are shown in Table 2. Noticing that we use multi-gpu synchronized batch normalization during training as in [34]…”

Section: Resultsmentioning

confidence: 99%

DetNet: Design Backbone for Object Detection

Peng²,

Yu³

et al. 2018

Lecture Notes in Computer Science

Self Cite

362

241

View full text Add to dashboard Cite

show abstract

“…Although we do not fine-tune batch normalization (BN) layers within the backbone for simplicity, we still achieve comparable results with the state-of-the-art semantic segmentation networks like PSPNet. Based on common practice in semantic [4,39] and instance segmentation [29,24], we expect the performance to be further improved with BN layers fine-tuned. Our UPSNet contains 8 loss functions in total: semantic segmentation head (whole image and RoI based pixel-wise classification losses), panoptic segmentation head (whole image based pixel-wise classification loss), RPN (box classification, box regression) and instance segmentation head (box classification, box regression and mask segmentation).…”

Section: Trainingmentioning

confidence: 99%

UPSNet: A Unified Panoptic Segmentation Network

Xiong

Liao

Zhao

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

414

331

View full text Add to dashboard Cite

In this paper, we propose a unified panoptic segmentation network (UPSNet) for tackling the newly proposed panoptic segmentation task. On top of a single backbone residual network, we first design a deformable convolution based semantic segmentation head and a Mask R-CNN style instance segmentation head which solve these two subtasks simultaneously. More importantly, we introduce a parameter-free panoptic head which solves the panoptic segmentation via pixel-wise classification. It first leverages the logits from the previous two heads and then innovatively expands the representation for enabling prediction of an extra unknown class which helps better resolve the conflicts between semantic and instance segmentation. Additionally, it handles the challenge caused by the varying number of instances and permits back propagation to the bottom modules in an end-to-end manner. Extensive experimental results on Cityscapes, COCO and our internal dataset demonstrate that our UPSNet achieves stateof-the-art performance with much faster inference.

show abstract

“…Two-Step Framework Our work follows the two-step approach. A two-step approach first detects human proposals [25,22] and then performs single person pose estimation [20,33]. The state-of-the-art two-step methods [8,32,13,14] achieve significantly higher scores than the part-based methods.…”

Section: Multi-person Pose Estimationmentioning

confidence: 99%

CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark

Wang²,

Zhu

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

466

236

View full text Add to dashboard Cite

Multi-person pose estimation is fundamental to many computer vision tasks and has made significant progress in recent years. However, few previous methods explored the problem of pose estimation in crowded scenes while it remains challenging and inevitable in many scenarios. Moreover, current benchmarks cannot provide an appropriate evaluation for such cases. In this paper, we propose a novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms. Our model consists of two key components: joint-candidate single person pose estimation (SPPE) and global maximum joints association. With multipeak prediction for each joint and global association using graph model, our method is robust to inevitable interference in crowded scenes and very efficient in inference. The proposed method surpasses the state-of-the-art methods on CrowdPose dataset by 5.2 mAP and results on MSCOCO dataset demonstrate the generalization ability of our method. Source code and dataset will be made publicly available.

show abstract

MegDet: A Large Mini-Batch Object Detector

Cited by 27 publications

References 17 publications

DetNet: Design Backbone for Object Detection

DetNet: Design Backbone for Object Detection

UPSNet: A Unified Panoptic Segmentation Network

CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark

Contact Info

Product

Resources

About