HoughNet: Integrating Near and Long-Range Evidence for Bottom-Up Object Detection

Download

index.pdf

Date

2020-01-01

Author

Samet, Nermin
Hicsonmez, Samet
Akbaş, Emre

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

184
views

66
downloads

This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby generalizing and enhancing current object detection methodology, which typically relies on only local evidence. On the COCO dataset, HoughNet’s best model achieves 46.4 AP (and 65.1 AP50), performing on par with the state-of-the-art in bottom-up object detection and outperforming most major one-stage and two-stage methods. We further validate the effectiveness of our proposal in another task, namely, “labels to photo” image generation by integrating the voting module of HoughNet to two different GAN models and showing that the accuracy is significantly improved in both cases. Code is available at https://github.com/nerminsamet/houghnet.

Subject Keywords

Object detection, Voting, Bottom-up recognition, Hough transform, Image-to-image translation

URI

https://hdl.handle.net/11511/94066

DOI

https://doi.org/10.1007/978-3-030-58595-2_25

Conference Name

16th European Conference on Computer Vision, ECCV 2020

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

HoughNet: Integrating Near and Long-Range Evidence for Visual Detection Samet, Nermin; Hicsonmez, Samet; Akbaş, Emre (2022-1-01) IEEEThis paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby...
Integrating near and long-range evidence for visual detection Samet, Nermin; Akbaş, Emre; Department of Computer Engineering (2021-9) This thesis presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby ge...
HYPERSPECTRAL UNMIXING BASED VEGETATION DETECTION WITH SEGMENTATION Özdemir, Okan Bilge; Soydan, Hilal; Çetin, Yasemin; Duzgun, Sebnem (2016-07-15) This paper presents a vegetation detection application with semi-supervised target detection using hyperspectral unmixing and segmentation algorithms. The method firstly compares the known target spectral signature from a generic source such as a spectral library with each pixel of hyperspectral data cube employing Spectral Angle Mapper (SAM) algorithm. The pixel(s) with the best match are assumed to be the most likely target vegetation locations. The regions around these potential target locations are furt...
Moving object detection with supervised learning methods Köksal, Aybora; Alatan, Abdullah Aydın; İnce, Kutalmış Gökalp; Department of Electrical and Electronics Engineering (2021-9-7) In this thesis, single target object detection problem is examined. Object detection is a problem that aims defining all of the objects of interest with their pre-defined classes in an image, or in a series of images. The main objective of this thesis is to exploit spatio-temporal information for performance enhancement during moving object detection. To this extent, modern object detection algorithms which are based on CNN architectures are analyzed. Based on this analysis, state-of-the-art techniques whic...
Segmentation Driven Object Detection with Fisher Vectors Cinbiş, Ramazan Gökberk; Schmid, Cordelia (2013-01-01) We present an object detection system based on the Fisher vector (FV) image representation computed over SIFT and color descriptors. For computational and storage efficiency, we use a recent segmentation-based method to generate class-independent object detection hypotheses, in combination with data compression techniques. Our main contribution is a method to produce tentative object segmentation masks to suppress background clutter in the features. Re-weighting the local image features based on these masks...

Citation Formats

N. Samet, S. Hicsonmez, and E. Akbaş, “HoughNet: Integrating Near and Long-Range Evidence for Bottom-Up Object Detection,” Glasgow, İngiltere, 2020, vol. 12370 LNCS, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/94066.