object detection; robust detection; ACM MM21 grand challenge; Security AI Challenger Phase VII

Overview

赛题背景

在商品知识产权领域,知识产权体现为在线商品的设计和品牌。不幸的是,在每一天,存在着非法商户通过一些对抗手段干扰商标识别来逃避侵权,这带来了很高的知识产权风险和财务损失。为了促进先进的多媒体人工智能技术的发展,以保护企业来之不易的创作和想法免受恶意使用和剽窃,因此提出了鲁棒性标识检测挑战赛 (ACM MM2021 Robust Logo Detection)。挑战赛需要参赛者处理小目标检测长尾对象类别对抗性干扰图像。这一挑战集中于现实世界机器学习和多媒体系统中安全问题的最新研究和未来方向。

前言

  • 本方案初赛排名 TOP 6,复赛排名 TOP 2,综合排名 TOP 2
  • 特别感谢阿里安全组织的这场比赛,一方面锻炼了我们的能力,一方面给了我们探索实际业务场景中各种困难的机会;

赛题攻关

检测模型的选取:

我们选择了detectoRS作为我们的检测模型,该模型当前在目标检测coco排行榜排名第七,我们选择了其级联的框架。Cascade_detectoRS网络结构如下:

framework

其中SAC (Switchable Atrous Convolution) 表示可切换的空洞卷积,它可以自适应选择感受野 ,其中 RFP (Recursive Feature Pyramid)采用循环结构来反复利用和精炼提取的特征,“H”表示检测头,我们使用了广泛使用的三级级联结构,“B”表示回归框,“C”表示类别预测结果,“B0”表示RPN网络的输出结果。除此之外,整个网络模型还使用了基于注意力的特征融合机制和类似SENet的全局上下文模块来增强网络的表征能力。显而易见,该网络结构基本集合了常见的检测涨点的tricks。对于backbone的选取,一般而言,越大越复杂的特征提取网络,往往具有较好的性能表现,通过对网络复杂程度与训练耗时tradeoff的多次实验和思考,我们最终选择了ResNet50作为基本的网络,并将网络中标准的3*3卷积换成SAC卷积模块。

小目标处理策略:

对于小目标问题,我们并没有单独地去设计网络模块或者对数据进行小目标增广处理。由于网络模型的backbone是基于ResNet50的,所以我们可以使用较大尺度的输入,比如800,900,1000等。在兼顾小目标检测问题的同时,如何提升检测性能也是很重要的,在实验中我们采用了多尺度训练的机制,训练尺度最大边长为1333,短边尺度范围为800~1100。

长尾分布处理:

对于长尾数据的处理,容易想到的处理方案有重采样和均衡损失这两种。正如前面所介绍的那样,重采样会增加训练的时间,而且采样率也不容易设置,对于大数据集很不友好。均衡损失,往往是通过对类别项概率进行权重矫正实现的。这种方案的缺陷在于忽略了背景候选区域的影响。此外,固定的权重值不一定适合不同训练阶段网络的学习。因此,我们使用了EQ-Loss V2作为检测模型中的分类损失函数,RPN处的分类损失,我们依然使用交叉熵损失函数。EQL_V2 loss的特点是基于梯度引导的,它根据正梯度与负梯度的累积比,分别对正负梯度进行加权矫正。

对抗干扰的处理:

从初赛到复赛,我们都使用了multi-scale testing。尺度范围在训练尺度范围的基础我增加了(1333,1200),这种较大尺度的使用主要作用在于提升小目标检测的recall值以及提升模型鲁棒性。当然我们也尝试了一系列图像数字领域防御的方法,例如 JPEG compression,quantization,denoise 等经典的手段,这些方法都会造成检测性能的下降,其主要的原因在于测试数据集中包含图像数字攻击的对抗样本很少,绝大多数的对抗样本基本都是无限制攻击下产生的扰动,这些扰动的生成和常见的防御机理存在很大程度的不一致性,因此这些方法基本没有任何防御效果。甚至由于防御造成的信息损失,导致最终正常图片性能的下降。 因此,对于对抗干扰的可能有效的处理方法,是模拟当前噪声的生成,通过增广数据来提升模型的鲁棒性,我们尝试加Gaussian噪声、加雨、加雾、图像模糊化等方法,有一定程度的性能提升效果。

检测效果图:

results

一些思考:

通过此次比赛,我们发现其实每个检测模型都可以很鲁棒,这种鲁棒性并不需要特定的网络结构,模型鲁棒性很大程度取决于训练后网络收敛的位置点,不同的收敛点往往具有较大的鲁棒性差别。如何研究出有效的网络训练策略或许会是网络鲁棒性的基本保证! 💥

Paper Link: https://arxiv.org/abs/2108.00422

checkpoint: Link:https://pan.baidu.com/s/1u12MAVgoIke6HobJLfbebg

Password:6j2o

Please cite:

@misc{jia2021effective, title={An Effective and Robust Detector for Logo Detection}, author={Xiaojun Jia and Huanqian Yan and Yonglin Wu and Xingxing Wei and Xiaochun Cao and Yong Zhang}, year={2021}, eprint={2108.00422}, archivePrefix={arXiv}, primaryClass={cs.CV} }

Owner
student
Easily pull telemetry data and create beautiful visualizations for analysis.

This repository is a work in progress. Anything and everything is subject to change. Porpo Table of Contents Porpo Table of Contents General Informati

Ryan Dawes 33 Nov 30, 2022
Implementation of UNET architecture for Image Segmentation.

Semantic Segmentation using UNET This is the implementation of UNET on Carvana Image Masking Kaggle Challenge About the Dataset This dataset contains

Anushka agarwal 4 Dec 21, 2021
PURE: End-to-End Relation Extraction

PURE: End-to-End Relation Extraction This repository contains (PyTorch) code and pre-trained models for PURE (the Princeton University Relation Extrac

Princeton Natural Language Processing 657 Jan 09, 2023
使用深度学习框架提取视频硬字幕;docker容器免安装深度学习库,使用本地api接口使得界面和后端识别分离;

extract-video-subtittle 使用深度学习框架提取视频硬字幕; 本地识别无需联网; CPU识别速度可观; 容器提供API接口; 运行环境 本项目运行环境非常好搭建,我做好了docker容器免安装各种深度学习包; 提供windows界面操作; 容器为CPU版本; 视频演示 https

歌者 16 Aug 06, 2022
A set of simple scripts to process the Imagenet-1K dataset as TFRecords and make index files for NVIDIA DALI.

Overview This is a set of simple scripts to process the Imagenet-1K dataset as TFRecords and make index files for NVIDIA DALI. Make TFRecords To run t

8 Nov 01, 2022
[CVPR 2021] NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning

NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning Project Page | Paper | Supplemental material #1 | Supplement

KAIST VCLAB 49 Nov 24, 2022
POPPY (Physical Optics Propagation in Python) is a Python package that simulates physical optical propagation including diffraction

POPPY: Physical Optics Propagation in Python POPPY (Physical Optics Propagation in Python) is a Python package that simulates physical optical propaga

Space Telescope Science Institute 132 Dec 15, 2022
Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

An official implementation of paper Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

11 Nov 23, 2022
Improving Factual Completeness and Consistency of Image-to-text Radiology Report Generation

Improving Factual Completeness and Consistency of Image-to-text Radiology Report Generation The reference code of Improving Factual Completeness and C

46 Dec 15, 2022
An open-source outlier detection package by Getcontact Data Team

pyfbad The pyfbad library supports anomaly detection projects. An end-to-end anomaly detection application can be written using the source codes of th

Teknasyon Tech 41 Dec 27, 2022
Histocartography is a framework bringing together AI and Digital Pathology

Documentation | Paper Welcome to the histocartography repository! histocartography is a python-based library designed to facilitate the development of

155 Nov 23, 2022
Sign-to-Speech for Sign Language Understanding: A case study of Nigerian Sign Language

Sign-to-Speech for Sign Language Understanding: A case study of Nigerian Sign Language This repository contains the code, model, and deployment config

16 Oct 23, 2022
Autotype on websites that have copy-paste disabled like Moodle, HackerEarth contest etc.

Autotype A quick and small python script that helps you autotype on websites that have copy paste disabled like Moodle, HackerEarth contests etc as it

Tushar 32 Nov 03, 2022
Kalidokit is a blendshape and kinematics solver for Mediapipe/Tensorflow.js face, eyes, pose, and hand tracking models

Blendshape and kinematics solver for Mediapipe/Tensorflow.js face, eyes, pose, and hand tracking models.

Rich 4.5k Jan 07, 2023
Barlow Twins and HSIC

Barlow Twins and HSIC Unofficial Pytorch implementation for Barlow Twins and HSIC_SSL on small datasets (CIFAR10, STL10, and Tiny ImageNet). Correspon

Yao-Hung Hubert Tsai 49 Nov 24, 2022
[CVPR2021] The source code for our paper 《Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning》.

TBE The source code for our paper "Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Le

Jinpeng Wang 150 Dec 28, 2022
GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily

GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily Abstract Graph Neural Networks (GNNs) are widely used on a

10 Dec 20, 2022
[ACM MM 2021] TSA-Net: Tube Self-Attention Network for Action Quality Assessment

Tube Self-Attention Network (TSA-Net) This repository contains the PyTorch implementation for paper TSA-Net: Tube Self-Attention Network for Action Qu

ShunliWang 18 Dec 23, 2022
Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing

Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing Paper Introduction Multi-task indoor scene understanding is widely considered a

62 Dec 05, 2022
[CVPR'21] Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation

Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation Weixiang Yang, Qi Li, Wenxi Liu, Yuanlong Yu, Y

118 Dec 26, 2022