# AttentionNet: Aggregating Weak Directions for Accurate Object Detection

arXiv: https://arxiv.org/abs/1506.07704 · HTML: https://mlsanity.com/paper/1506.07704/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2015.

## Built on by (most cited first, 10 of 10)

- [Face.evoLVe: A High-Performance Face Recognition Library](https://mlsanity.com/paper/2107.08621/) (2021)
- [Causal Reasoning Meets Visual Representation Learning: A Prospective Study](https://mlsanity.com/paper/2204.12037/) (2022)
- [AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes](https://mlsanity.com/paper/2106.10409/) (2021)
- [Oriented object detection in optical remote sensing images using deep learning: a survey](https://mlsanity.com/paper/2302.10473/) (2023)
- [AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale](https://mlsanity.com/paper/2404.03482/) (2024)
- [Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning](https://mlsanity.com/paper/2105.04113/) (2021)
- [Hybrid attention network based on progressive embedding scale-context for crowd counting](https://mlsanity.com/paper/2106.02324/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Design and Implementation of A Soccer Ball Detection System with Multiple Cameras](https://mlsanity.com/paper/2302.00123/) (2023)
- [A Novel Strategy for Improving Robustness in Computer Vision Manufacturing Defect Detection](https://mlsanity.com/paper/2305.09407/) (2023)

## Abstract (arXiv)

We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet provides quantized weak directions pointing a target object and the ensemble of iterative predictions from AttentionNet converges to an accurate object boundary box. Since AttentionNet is a unified network for object detection, it detects objects without any separated models from the object proposal to the post bounding-box regression. We evaluate AttentionNet by a human detection task and achieve the state-of-the-art performance of 65% (AP) on PASCAL VOC 2007/2012 with an 8-layered architecture only.