AttentionNet: Aggregating Weak Directions for Accurate Object Detection

By Donggeun Yoo, Sunggyun Park, Joon-Young Lee, Anthony S. Paek, In-So Kweon. 2015

167 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Cascade R-CNN: High Quality Object Detection and Instance Segmentation (2019, methodology): “[42], [61] proposed an alternative procedure to localize objects sequentially.”
Cascade R-CNN: Delving Into High Quality Object Detection (2017, neutral): “[37, 27] also attempted to localize objects sequentially.”
Attention to Scale: Scale-Aware Semantic Image Segmentation (2015, methodology): “Attention models for deep networks: In computer vision, attention models have been used widely used for image classification [8, 25, 53] and object detection [4, 7, 57].”
Recent advances in convolutional neural networks (2015, background): “[138] treats the object detection problem as an iterative classification problem.”
Single-Shot Refinement Neural Network for Object Detection (2017, methodology): “After that, numerous effective techniques are proposed to further improve the performance, such as architecture diagram [5, 25, 55], training strategy [31, 41, 48, 50], contextual reasoning [1, 14, 40, 51] and multiple layers exploiting [3, 24, 26, 42].”
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization (2016, neutral): “Note that active localization schemes have also been previously applied in the object detection literature [4, 13, 14, 17, 30, 39, 42].”
On the Detection of Digital Face Manipulation (2019, methodology): “In computer vision, attention models have been widely used for image classification [9, 47, 43], image inpainting [27, 51] and object detection [50, 8].”
Object Detection With Deep Learning: A Review (2018, methodology): “The regression/classification based methods mainly includes MultiBox [68], AttentionNet [69],”
Spatial Memory for Context Reasoning in Object Detection (2017, background): “Another commonly used trick especially beneﬁcial for reducing localization error is iterative bounding box reﬁne-ment [25, 26, 69, 95], which leverages local image context to predict a better bounding box iteratively.”
Learned Contextual Feature Reweighting for Image Geo-Localization (2017, background): “Much research has been done in the areas of feature selection, attention, and saliency [20, 63, 37].”
A Survey on Performance Metrics for Object-Detection Algorithms (2020, methodology): “Works found in the literature [1], [9], [12]–[20], [37] usually neither mention the method used nor reference the adopted tool to evaluate their results.”
State of the Art in Defect Detection Based on Machine Vision (2021, methodology): “The regression-and classification-based methods mainly include MultiBox [201], AttentionNet [202], G-CNN [203], You Only Look Once (YOLO) [204], the single-shot MultiBox detector (SSD) [205], YOLOv2 [206], RetinaNet [207], YOLOv3 [208], and YOLOv4 [209].”
Object Detection in 20 Years: A Survey (2019, methodology): “Sub-region search [184, 256–258] provides a new way of performing detection.”