ReDet: A Rotation-equivariant Detector for Aerial Object Detection

Han, Jiaming; Ding, Jian; Xue, Nan; Xia, Gui-Song

doi:10.1109/cvpr46437.2021.00281

Cited by 368 publications

(126 citation statements)

References 27 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…Similar works for the aerial images have also been undertaken by Jiaming Han et.al, who propose the so-called oriented detection module (ODM) and feature alignment module (FAM) (24,25).…”

Section: Introductionmentioning

confidence: 87%

Towards Toxic and Narcotic Medication Detection with Rotated Object Detector

Jiao¹,

Wang²,

Fu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent years have witnessed the advancement of deep learning vision technologies and applications in the medical industry. Intelligent devices for special medication management are in great need of, which requires more precise detection algorithms to identify the specifications and locations.In this work, YOLO (You only look once) based object detectors are tailored for toxic and narcotic medications detection tasks. Specifically, a more flexible annotation with rotated degree ranging from 0 • to 90 • and a mask-mapping-based non-maximum suppression method are proposed to achieve a feasible and efficient medication detector aiming at arbitrarily oriented bounding boxes. Extensive experiments demonstrate that the rotated YOLO detectors are more suitable for identifying densely arranged drugs. The best shot mean average precision of the proposed network reaches 0.811 while the inference time is less than 300ms.

show abstract

“…Similar works for the aerial images have also been undertaken by Jiaming Han et.al, who propose the so-called oriented detection module (ODM) and feature alignment module (FAM) (24,25).…”

Section: Introductionmentioning

confidence: 87%

Towards Toxic and Narcotic Medication Detection with Rotated Object Detector

Jiao¹,

Wang²,

Fu³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the experiment part, there are six comparison networks, namely faster R-CNN [8], oriented R-CNN [16], ReDet [25], RoITransformer [17], double-head [15], and IPC-Det (ours). There are four experimental indicators: "mAP", "AP", "AR", "Params", "FPS".…”

Section: Comparision With Other Networkmentioning

confidence: 99%

“…Ref. [25] incorporates a rotation-equivariant network in the detector to extract rotation-equivariant features, which can accurately predict orientation and lead to a huge reduction in model size. Based on the rotation-equivariant features, a rotation-invariant RoI alignment (RiRoI Align) is also proposed, which adaptively extracts rotation-invariant features from the equivariant features according to the orientation of the RoI.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Imaging Parameters-Considered Slender Target Detection in Optical Satellite Images

et al. 2022

View full text Add to dashboard Cite

The existing slender target detection methods based on optical satellite images are greatly affected by the satellite perspective and the solar perspective. Due to limited data sources, it is difficult to implement a fully data-driven approach. This work introduces the imaging parameters of optical satellite images, which greatly reduces the influence of the satellite perspectives and the solar perspectives, and reduces the demand for the amount of data. We improve the oriented bounding box (OBB) detector based on faster R-CNN (region convolutional neural networks) and propose an imaging parameters-considered detector (IPC-Det) which is more suitable for our task. Specifically, in the first stage, the umbra and the shadow are extracted by horizontal bounding box (HBB), respectively, and then the matching of the umbra and the shadow is realized according to the imaging parameters. In the second stage, the paired umbra and shadow features are used to complete the classification and regression, and the target is obtained by OBB. In experiments, after introducing imaging parameters, our detection accuracy is improved by 3.9% (up to 87.5%), proving that this work is a successful attempt to introduce imaging parameters for slender target detection.

show abstract

“…The aforementioned methods consider equivariance to specific transformations until Weiler et al [44] provide a general solution of kernel space constraint for arbitrary group representations of the Euclidean group E(2). From the perspective of an application, Han et al [16] and Gupta et al [15] extract rotationequivariant feature maps for oriented object detection and visual tracking, respectively. We leverage E(2)-equivariant CNNs [44] as a building block of our network to perceive consistent symmetry patterns across multiple orientations.…”

Section: Equivariant Deep Learningmentioning

confidence: 99%

Reflection and Rotation Symmetry Detection via Equivariant Learning

Seo¹,

Kim²,

Kwak³

et al. 2022

Preprint

View full text Add to dashboard Cite

The inherent challenge of detecting symmetries stems from arbitrary orientations of symmetry patterns; a reflection symmetry mirrors itself against an axis with a specific orientation while a rotation symmetry matches its rotated copy with a specific orientation. Discovering such symmetry patterns from an image thus benefits from an equivariant feature representation, which varies consistently with reflection and rotation of the image. In this work, we introduce a group-equivariant convolutional network for symmetry detection, dubbed EquiSym, which leverages equivariant feature maps with respect to a dihedral group of reflection and rotation. The proposed network is built end-toend with dihedrally-equivariant layers and trained to output a spatial map for reflection axes or rotation centers. We also present a new dataset, DENse and DIverse symmetry (DENDI), which mitigates limitations of existing benchmarks for reflection and rotation symmetry detection. Experiments show that our method achieves the state of the arts in symmetry detection on LDRS and DENDI datasets.

show abstract

ReDet: A Rotation-equivariant Detector for Aerial Object Detection

Cited by 368 publications

References 27 publications

Towards Toxic and Narcotic Medication Detection with Rotated Object Detector

Towards Toxic and Narcotic Medication Detection with Rotated Object Detector

Imaging Parameters-Considered Slender Target Detection in Optical Satellite Images

Reflection and Rotation Symmetry Detection via Equivariant Learning

Contact Info

Product

Resources

About