Scale-Transferrable Object Detection

Zhou, Peng; Ni, Bingbing; Geng, C.; Hu, Jingyan; Xu, Yi

doi:10.1109/cvpr.2018.00062

Cited by 340 publications

(188 citation statements)

References 13 publications

Supporting

Mentioning

187

Contrasting

Unclassified

Order By: Relevance

“…These methods build their architecture on the backbone features and ignore the top-down pathway of FPN by employing different feature integration mechanisms, as displayed in Figure 10(c-h). Scale-Transferrable Detection Network (STDN) [72] generates the pyramidal features from the last layer of the backbone features which are extracted using DenseNet [106] blocks (Figure 10(c)). In a DenseNet block, all the lower level features are propagated to every next layer within a block.…”

Section: Methods Using Backbone Features As a Basismentioning

confidence: 99%

Imbalance Problems in Object Detection: A Review

Öksüz

Cam

Kalkan

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

416

171

View full text Add to dashboard Cite

In this paper, we present a comprehensive review of the imbalance problems in object detection. To analyze the problems in a systematic manner, we introduce two taxonomies; one for the problems and the other for the proposed solutions. Following the taxonomy for the problems, we discuss each problem in depth and present a unifying yet critical perspective on the solutions in the literature. In addition, we identify major open issues regarding the existing imbalance problems as well as imbalance problems that have not been discussed before. Moreover, in order to keep our review up to date, we provide an accompanying webpage which categorizes papers addressing imbalance problems, according to our problem-based taxonomy. Researchers can track newer studies on this webpage available at: https://github.com/kemaloksuz/ObjectDetectionImbalance.

show abstract

Section: Methods Using Backbone Features As a Basismentioning

confidence: 99%

Imbalance Problems in Object Detection: A Review

Öksüz

Cam

Kalkan

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

416

171

View full text Add to dashboard Cite

show abstract

“…In order to efficiently train the hierarchical domain feature alignment module, inspired by [41], we introduce a scale reduction module (SRM) which aims at down-scaling the feature maps without information loss. Specifically, SRM contains two steps: 1) A 1 × 1 convolution layer is implemented to reduce the number of channels of feature maps in each block.…”

Section: Hierarchical Domain Feature Alignmentmentioning

confidence: 99%

Multi-Adversarial Faster-RCNN for Unrestricted Object Detection

Zhang

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

334

227

View full text Add to dashboard Cite

Conventional object detection methods essentially suppose that the training and testing data are collected from a restricted target domain with expensive labeling cost. For alleviating the problem of domain dependency and cumbersome labeling, this paper proposes to detect objects in unrestricted environment by leveraging domain knowledge trained from an auxiliary source domain with sufficient labels. Specifically, we propose a multi-adversarial Faster-RCNN (MAF) framework for unrestricted object detection, which inherently addresses domain disparity minimization for domain adaptation in feature representation. The paper merits are in three-fold: 1) With the idea that object detectors often becomes domain incompatible when image distribution resulted domain disparity appears, we propose a hierarchical domain feature alignment module, in which multiple adversarial domain classifier submodules for layerwise domain feature confusion are designed; 2) An information invariant scale reduction module (SRM) for hierarchical feature map resizing is proposed for promoting the training efficiency of adversarial domain adaptation; 3) In order to improve the domain adaptability, the aggregated proposal features with detection results are feed into a proposed weighted gradient reversal layer (WGRL) for characterizing hard confused domain samples. We evaluate our MAF on unrestricted tasks including Cityscapes, KITTI, Sim10k, etc. and the experiments show the state-of-the-art performance over the existing detectors.

show abstract

“…Corner-based methods There is a need to train a robust and discriminative feature embedding of objects to obtain a good detection performance. In Some techniques such as dilated/atrous convolutions [97,52] were proposed to avoid downsampling, and used the high reso- were later developed [109,110,109,111,112,92,113,114,115,116,117,118,119], with modifications to the feature pyramid block (see Fig. 8).…”

Section: Keypoints-based Methodsmentioning

confidence: 99%

Recent advances in deep learning for object detection

2020

View full text Add to dashboard Cite

Object detection is a fundamental visual recognition problem in computer vision and has been widely studied in the past decades.Visual object detection aims to find objects of certain target classes with precise localization in a given image and assign each object instance a corresponding class label. Due to the tremendous successes of deep learning based image classification, object detection techniques using deep learning have been actively studied in recent years. In this paper, we give a comprehensive survey of recent advances in visual object detection with deep learning. By reviewing a large body of recent related work in literature, we systematically analyze the existing object detection frameworks and organize the survey into three major parts: (i) detection components, (ii) learning strategies, and (iii) applications & benchmarks. In the survey, we cover a variety of factors affecting the detection performance in detail, such as detector architectures, feature learning, proposal generation, sampling strategies, etc.Finally, we discuss several future directions to facilitate and spur future research for visual object detection with deep learning.

show abstract

Scale-Transferrable Object Detection

Cited by 340 publications

References 13 publications

Imbalance Problems in Object Detection: A Review

Imbalance Problems in Object Detection: A Review

Multi-Adversarial Faster-RCNN for Unrestricted Object Detection

Recent advances in deep learning for object detection

Contact Info

Product

Resources

About