# AttentionNet: Aggregating Weak Directions for Accurate Object Detection

Source: [AttentionNet: Aggregating Weak Directions for Accurate Object Detection](<https://www.sota2.com/research/paper/68fa62191e209131ce9f79f9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:13:30.351Z

Authors: Donggeun Yoo, Sunggyun Park, Joon-Young Lee, Anthony S. Paek, In So Kweon

Published: 2015-06-25T11:21:04.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1506.07704>)

[PDF](<https://arxiv.org/pdf/1506.07704.pdf>)