AttentionNet: Aggregating Weak Directions for Accurate Object Detection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationHuman DetectionObjectobject-detectionObject DetectionregressionSimilar Papers 제목 키워드 기반
Action-Driven Object Detection with Top-Down Visual Attentions
A dominant paradigm for deep learning based object detection relies on a "bottom-up" approach using "passive" scoring of class agnostic proposals. These approaches are efficient but lack of holistic analysis of scene-lev…
Objectobject-detectionObject DetectionImproving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion
With the increasing popularity of convolutional neural networks (CNNs), recent works on face-based age estimation employ these networks as the backbone. However, state-of-the-art CNN-based methods treat each facial regio…
Age EstimationBridging the Gap between Classification and Localization for Weakly Supervised Object Localization
Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. Most existing methods use a class activation map (CAM) to generate a loca…
ObjectObject LocalizationWeakly-Supervised Object LocalizationFuzzy Classification Aggregation
We consider the problem where a set of individuals has to classify $m$ objects into $p$ categories and does so by aggregating the individual classifications. We show that if $m\geq 3$, $m\geq p\geq 2$, and classification…
ClassificationAnti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization
Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide…
Adversarial AttackObjectObject LocalizationSemantic Segmentation+4