艾伯特FPN：深度学习对象检测中的多尺度特征金字塔网络
需积分: 25 122 浏览量
更新于2024-09-14
收藏 774KB PDF 举报
《艾伯特FPN：面向对象检测的特征金字塔网络》[aibbt.com]是一篇深度探讨在现代计算机视觉领域中如何利用深度卷积神经网络（Deep Convolutional Neural Networks, DCNN）构建高效且通用的特征金字塔结构的论文。传统的对象检测系统依赖于特征金字塔来捕捉不同尺度的物体信息，然而，近年来的深度学习对象检测器倾向于避免这种金字塔架构，主要原因是它们对计算资源和内存的需求较高。
论文的主要贡献者Tsung-Yi Lin、Piotr Dollár、Ross Girshick、Kaiming He、Bharath Hariharan和Serge Belongie来自Facebook AI Research (FAIR)和康奈尔大学，他们提出了一种名为Feature Pyramid Network (FPN)的新架构。FPN的设计灵感来源于DCNN固有的多层次、金字塔式的特性，它通过额外的计算成本，有效地构建了包含多尺度特征图的金字塔结构。
FPN的核心是采用一种自上而下的top-down方法，结合水平的侧向连接，这样可以在每个层级生成高分辨率的语义特征，这对于捕捉目标的精确位置和细节至关重要。这种方法不仅减少了对外部金字塔结构的依赖，而且简化了整个系统的复杂性。通过将FPN融入基本的Faster R-CNN系统，研究者们实现了单模型性能的显著提升，甚至在无需额外优化的情况下，就在COCO检测基准上超越了所有现有的单一模型，包括2016年COCO比赛的所有记录。
这个突破性的成果展示了FPN作为通用特征提取器的强大能力，它不仅提高了对象检测的准确性和效率，还为后续的深度学习模型设计提供了新的思考方向，特别是在实时和资源有限的应用场景中。对于那些关注计算机视觉和深度学习特别是对象检测领域的研究人员和工程师来说，这篇论文提供了深入理解并借鉴的关键信息。
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin
1,2
, Piotr Doll
´
ar
1
, Ross Girshick
1
,
Kaiming He
1
, Bharath Hariharan
1
, and Serge Belongie
2
1
Facebook AI Research (FAIR)
2
Cornell University and Cornell Tech
Abstract
Feature pyramids are a basic component in recognition
systems for detecting objects at different scales. But recent
deep learning object detectors have avoided pyramid rep-
resentations, in part because they are compute and memory
intensive. In this paper, we exploit the inherent multi-scale,
pyramidal hierarchy of deep convolutional networks to con-
struct feature pyramids with marginal extra cost. A top-
down architecture with lateral connections is developed for
building high-level semantic feature maps at all scales. This
architecture, called a Feature Pyramid Network (FPN),
shows significant improvement as a generic feature extrac-
tor in several applications. Using FPN in a basic Faster
R-CNN system, our method achieves state-of-the-art single-
model results on the COCO detection benchmark without
bells and whistles, surpassing all existing single-model en-
tries including those from the COCO 2016 challenge win-
ners. In addition, our method can run at 6 FPS on a GPU
and thus is a practical and accurate solution to multi-scale
object detection. Code will be made publicly available.
1. Introduction
Recognizing objects at vastly different scales is a fun-
damental challenge in computer vision. Feature pyramids
built upon image pyramids (for short we call these featur-
ized image pyramids) form the basis of a standard solution
[1] (Fig. 1(a)). These pyramids are scale-invariant in the
sense that an object’s scale change is offset by shifting its
level in the pyramid. Intuitively, this property enables a
model to detect objects across a large range of scales by
scanning the model over both positions and pyramid levels.
Featurized image pyramids were heavily used in the
era of hand-engineered features [5, 25]. They were so
critical that object detectors like DPM [7] required dense
scale sampling to achieve good results (e.g., 10 scales per
octave). For recognition tasks, engineered features have
(a) Featurized image pyramid
predict
predict
predict
predict
(b) Single feature map
predict
(d) Feature Pyramid Network
predict
predict
predict
(c) Pyramidal feature hierarchy
predict
predict
predict
Figure 1. (a) Using an image pyramid to build a feature pyramid.
Features are computed on each of the image scales independently,
which is slow. (b) Recent detection systems have opted to use
only single scale features for faster detection. (c) An alternative is
to reuse the pyramidal feature hierarchy computed by a ConvNet
as if it were a featurized image pyramid. (d) Our proposed Feature
Pyramid Network (FPN) is fast like (b) and (c), but more accurate.
In this figure, feature maps are indicate by blue outlines and thicker
outlines denote semantically stronger features.
largely been replaced with features computed by deep con-
volutional networks (ConvNets) [19, 20]. Aside from being
capable of representing higher-level semantics, ConvNets
are also more robust to variance in scale and thus facilitate
recognition from features computed on a single input scale
[15, 11, 29] (Fig. 1(b)). But even with this robustness, pyra-
mids are still needed to get the most accurate results. All re-
cent top entries in the ImageNet [33] and COCO [21] detec-
tion challenges use multi-scale testing on featurized image
pyramids (e.g., [16, 35]). The principle advantage of fea-
turizing each level of an image pyramid is that it produces
a multi-scale feature representation in which all levels are
semantically strong, including the high-resolution levels.
Nevertheless, featurizing each level of an image pyra-
mid has obvious limitations. Inference time increases con-
siderably (e.g., by four times [11]), making this approach
impractical for real applications. Moreover, training deep
1
arXiv:1612.03144v2 [cs.CV] 19 Apr 2017
www.aibbt.com 让未来触手可及
下载后可阅读完整内容，剩余9页未读，立即下载
151 浏览量
点击了解资源详情
点击了解资源详情
2021-10-10 上传
2021-10-08 上传
2021-09-08 上传
2021-09-08 上传
292 浏览量
248 浏览量
macair123
- 粉丝: 469
- 资源: 9
我的内容管理
展开
