Figure-ground representation in deep neural networks DOI
Brian Hu, Salman Khan, Ernst Niebur

и другие.

Опубликована: Март 1, 2019

Deep neural networks achieve state-of-the-art performance on many image segmentation tasks. However, the nature of learned representations used by these is unclear. Biological brains solve this task very efficiently and seemingly effortlessly. Neurophysiological recordings have begun to elucidate underlying mechanisms segmentation. In particular, it has been proposed that border ownership selectivity (BOS) first step in process brain. BOS a property an orientation selective neuron differentially respond object contour dependent location foreground (figure). We explored whether deep use close those biological brains, particular they explicitly represent BOS. therefore developed suite in-silico experiments test for BOS, similar probe primate tested two trained scene tasks (DOC [1] Mask R-CNN [2]), as well one network recognition (ResNet-50 [3]). Units ResNet50 predominantly showed contrast tuning. responded weakly stimuli. DOC network, we found units earlier layers stronger tuning, while deeper increasing tuning seems wide-spread extrastriate areas most common intermediate area V2 where prevalence neurons exceeds (V1) later (V4) areas. also which was natural images, did not generalize simple stimuli typically experiments. This differs from findings responses are than complex scenes. Our methods general can be applied other

Язык: Английский

Computer Vision – ECCV 2016 DOI Open Access
Bastian Leibe, Jiřı́ Matas, Nicu Sebe

и другие.

Lecture notes in computer science, Год журнала: 2016, Номер unknown

Опубликована: Янв. 1, 2016

Язык: Английский

Процитировано

207
Deep Nets: What have They Ever Done for Vision? DOI
Alan Yuille, Chenxi Liu

International Journal of Computer Vision, Год журнала: 2020, Номер 129(3), С. 781 - 802

Опубликована: Ноя. 27, 2020

Язык: Английский

Процитировано

73
An overview of edge and object contour detection DOI
Daipeng Yang, Bo Peng, Zaid Al‐Huda

и другие.

Neurocomputing, Год журнала: 2022, Номер 488, С. 470 - 493

Опубликована: Март 8, 2022

Язык: Английский

Процитировано

66
Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields DOI

Michaël Ramamonjisoa,

Yuming Du, Vincent Lepetit

и другие.

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Год журнала: 2020, Номер unknown, С. 14636 - 14645

Опубликована: Июнь 1, 2020

Current methods for depth map prediction from monocular images tend to predict smooth, poorly localized contours the occlusion boundaries in input image. This is unfortunate as are important cues recognize objects, and we show, may lead a way discover new objects scene reconstruction. To improve predicted maps, recent rely on various forms of filtering or an additive residual refine first estimate. We instead learn predict, given by some reconstruction method, 2D displacement field able re-sample pixels around into sharper reconstructions. Our method can be applied output any estimation end-to-end trainable fashion. For evaluation, manually annotated all test split popular NYUv2-Depth dataset. show that our approach improves localization state-of-the-art could evaluate, without degrading accuracy rest images.

Язык: Английский

Процитировано

58
Comprehensive review of edge and contour detection: from traditional methods to recent advances DOI
Qinyuan Huang, Jiasheng Huang

Neural Computing and Applications, Год журнала: 2025, Номер unknown

Опубликована: Янв. 5, 2025

Язык: Английский

Процитировано

1
RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth DOI
Mengyang Pu, Yaping Huang, Qingji Guan

и другие.

2021 IEEE/CVF International Conference on Computer Vision (ICCV), Год журнала: 2021, Номер unknown

Опубликована: Окт. 1, 2021

As a fundamental building block in computer vision, edges can be categorised into four types according to the discontinuity surface-Reflectance, Illumination, surface-Normal or Depth. While great progress has been made detecting generic individual of edges, it remains under-explored comprehensively study all edge together. In this paper, we propose novel neural network solution, RINDNet, jointly detect edges. Taking consideration distinct attributes each type and relationship between them, RINDNet learns effective representations for them works three stages. stage I, uses common backbone extract features shared by Then II branches prepare discriminative corresponding decoder. III, an independent decision head aggregates from previous stages predict initial results. Additionally, attention module maps capture underlying relations these are combined with results generate final detection For training evaluation, construct first public benchmark, BSDS-RIND, carefully annotated. our experiments, yields promising comparison state-of-the-art methods. Additional analysis is presented supplementary material.

Язык: Английский

Процитировано

39
DOOBNet: Deep Object Occlusion Boundary Detection from an Image DOI
Guoxia Wang, Xiaochuan Wang, Frederick W. B. Li

и другие.

Lecture notes in computer science, Год журнала: 2019, Номер unknown, С. 686 - 702

Опубликована: Янв. 1, 2019

Язык: Английский

Процитировано

26
Occlusion-Shared and Feature-Separated Network for Occlusion Relationship Reasoning DOI
Rui Lü, Feng Xue,

Menghan Zhou

и другие.

2021 IEEE/CVF International Conference on Computer Vision (ICCV), Год журнала: 2019, Номер unknown, С. 10342 - 10351

Опубликована: Окт. 1, 2019

Occlusion relationship reasoning demands closed contour to express the object, and orientation of each pixel describe order between objects. Current CNN-based methods neglect two critical issues task: (1) simultaneous existence relevance distinction for elements, i.e, occlusion edge orientation; (2) inadequate exploration features. For reasons above, we propose Occlusion-shared Feature-separated Network (OFNet). On one hand, considering orientation, sub-networks are designed share cue. other whole network is split into paths learn high semantic features separately. Moreover, a contextual feature prediction extracted, which represents bilateral cue foreground background areas. The then fused with precisely locate object regions. Finally, stripe convolution further aggregate from surrounding scenes edge. proposed OFNet remarkably advances state-of-the-art approaches on PIOD BSDS ownership dataset.

Язык: Английский

Процитировано

26
Deep Nets: What have they ever done for Vision? DOI Creative Commons
Alan Yuille, Chenxi Liu

arXiv (Cornell University), Год журнала: 2018, Номер unknown

Опубликована: Янв. 1, 2018

This is an opinion paper about the strengths and weaknesses of Deep Nets for vision. They are at heart enormous recent progress in artificial intelligence growing importance cognitive science neuroscience. have had many successes but also several limitations there limited understanding their inner workings. At present perform very well on specific visual tasks with benchmark datasets they much less general purpose, flexible, adaptive than human system. We argue that current form unlikely to be able overcome fundamental problem computer vision, namely how deal combinatorial explosion, caused by complexity natural images, obtain rich scenes achieves. this explosion takes us into a regime where "big data not enough" we need rethink our methods benchmarking performance evaluating vision algorithms. stress that, as algorithms increasingly used real world applications, evaluation merely academic exercise has important consequences world. It impractical review entire Net literature so restrict ourselves range topics references which intended entry points literature. The views expressed own do necessarily represent those anybody else community.

Язык: Английский

Процитировано

22
Figure-Ground Organization in Natural Scenes: Performance of a Recurrent Neural Model Compared with Neurons of Area V2 DOI Creative Commons
Brian Hu, R. von der Heydt, Ernst Niebur

и другие.

eNeuro, Год журнала: 2019, Номер 6(3), С. ENEURO.0479 - 18.2019

Опубликована: Май 1, 2019

A crucial step in understanding visual input is its organization into meaningful components, particular object contours and partially occluded background structures. This requires that all are assigned to either the foreground or (border ownership assignment). While earlier studies showed neurons primate extrastriate cortex signal border for simple geometric shapes, recent show consistent coding also complex natural scenes. In order understand how brain performs this task, we developed a biologically plausible recurrent neural network fully image computable. Our model uses local edge detector ( B ) cells grouping G whose activity represents proto-objects based on integration of feature information. send modulatory feedback connections those caused their activation, making selective. We found close agreement between our neurophysiological results terms timing signals (BOSs) as well consistency BOSs across benchmarked Berkeley Segmentation Dataset achieved performance comparable state-of-the-art computer vision approaches. proposed provides insight cortical mechanisms figure-ground organization.

Язык: Английский

Процитировано

19