This paper presents HoughNet, a one-stage, anchor-free, voting-based,\nbottom-up object detection method. Inspired by the Generalized Hough Transform,\nHoughNet determines the presence of an object at a certain location by the sum\nof the votes cast on that location. Votes are collected from both near and\nlong-distance locations based on a log-polar vote field. Thanks to this voting\nmechanism, HoughNet is able to integrate both near and long-range,\nclass-conditional evidence for visual recognition, thereby generalizing and\nenhancing current object detection methodology, which typically relies on only\nlocal evidence. On the COCO dataset, HoughNet's best model achieves 46.4 $AP$\n(and 65.1 $AP_{50}$), performing on par with the state-of-the-art in bottom-up\nobject detection and outperforming most major one-stage and two-stage methods.\nWe further validate the effectiveness of our proposal in another task, namely,\n"labels to photo" image generation by integrating the voting module of HoughNet\nto two different GAN models and showing that the accuracy is significantly\nimproved in both cases. Code is available at\nhttps://github.com/nerminsamet/houghnet.\n