A MultiPath Network for Object Detection

Zagoruyko, Sergey; Lerer, Adam; Lin, Tsung-Yi; Pinheiro, Pedro O.; Gross, Sam; Chintala, Soumith; Dollár, Piotr

doi:10.5244/c.30.15

Cited by 166 publications

(126 citation statements)

References 31 publications

Supporting

Mentioning

125

Contrasting

Order By: Relevance

“…Training data: "07"←VOC2007 trainval; "07T"←VOC2007 trainval and test; "12"←VOC2012 trainval; CO← COCO trainval. The COCO detection results were reported with COCO2015 Test-Dev, except for MPN [302] which reported with COCO2015 Test-Standard. Use Conv-deconv, as shown in Fig.…”

Section: Handling Of Object Scale Variationsmentioning

confidence: 92%

Deep Learning for Generic Object Detection: A Survey

et al. 2019

View full text Add to dashboard Cite

Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

show abstract

Section: Handling Of Object Scale Variationsmentioning

confidence: 92%

Deep Learning for Generic Object Detection: A Survey

et al. 2019

View full text Add to dashboard Cite

show abstract

“…where U is a set of IoU thresholds. This is closely related to the integral loss of [34], in which U = {0.5, 0.55, · · · , 0.75}, designed to fit the evaluation metric of the COCO challenge. By definition, the classifiers need to be ensembled at inference.…”

Section: Detection Qualitymentioning

confidence: 99%

Cascade R-CNN: Delving Into High Quality Object Detection

Cai

Vasconcelos

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

4,675

2,558

View full text Add to dashboard Cite

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance tends to degrade with increasing the IoU thresholds. Two main factors are responsible for this: 1) overfitting during training, due to exponentially vanishing positive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the input hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these problems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives. The detectors are trained stage by stage, leveraging the observation that the output of a detector is a good distribution for training the next higher quality detector. The resampling of progressively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reducing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset. Experiments also show that the Cascade R-CNN is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. The code will be made available at https://github.com/zhaoweicai/cascade-rcnn.

show abstract

“…But the offsets are static model parameters fixed after training and shared over different spatial locations. In a multi-path network for object detection [40], multiple RoIpooling layers are employed for each input RoI to better exploit multi-scale and context information. The multiple RoIpooling layers are centered at the input RoI, and are of different spatial scales.…”

Section: Related Workmentioning

confidence: 99%

Deformable ConvNets V2: More Deformable, Better Results

Zhu

Lin

et al. 2019

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

1,751

987

View full text Add to dashboard Cite

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural features conforms more closely than regular ConvNets to object structure, this support may nevertheless extend well beyond the region of interest, causing features to be influenced by irrelevant image content. To address this problem, we present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training. The modeling power is enhanced through a more comprehensive integration of deformable convolution within the network, and by introducing a modulation mechanism that expands the scope of deformation modeling. To effectively harness this enriched modeling capability, we guide network training via a proposed feature mimicking scheme that helps the network to learn features that reflect the object focus and classification power of R-CNN features. With the proposed contributions, this new version of Deformable ConvNets yields significant performance gains over the original model and produces leading results on the COCO benchmark for object detection and instance segmentation. * This work is done when Xizhou Zhu is an intern at Microsoft Research Asia.

show abstract

A MultiPath Network for Object Detection

Cited by 166 publications

References 31 publications

Deep Learning for Generic Object Detection: A Survey

Deep Learning for Generic Object Detection: A Survey

Cascade R-CNN: Delving Into High Quality Object Detection

Deformable ConvNets V2: More Deformable, Better Results

Contact Info

Product

Resources

About