Dogs vs. Cats

Dogs vs. Cats is a competition on Kaggle, which needs to write an algorithm to classify whether images contain either a dog or a cat. The training archive contains 25,000 images of dogs and cats. Web services are often protected with a challenge that's supposed to be easy for people to solve, but difficult for computers. Such a challenge is often called a CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) or HIP (Human Interactive Proof). HIPs are used for many purposes, such as to reduce email and blog spam and prevent brute-force attacks on web site passwords. Asirra (Animal Species Image Recognition for Restricting Access) is a HIP that works by asking users to identify photographs of cats and dogs. This task is difficult for computers, but studies have shown that people can accomplish it quickly and accurately. Many even think it's fun! Asirra is unique because of its partnership with Petfinder.com, the world's largest site devoted to finding homes for homeless pets. They've provided Microsoft Research with over three million images of cats and dogs, manually classified by people at thousands of animal shelters across the United States. Kaggle is fortunate to offer a subset of this data for fun and research. While random guessing is the easiest form of attack, various forms of image recognition can allow an attacker to make guesses that are better than random. There is enormous diversity in the photo database (a wide variety of backgrounds, angles, poses, lighting, etc.), making accurate automatic classification difficult. In an informal poll conducted many years ago, computer vision experts posited that a classifier with better than 60% accuracy would be difficult without a major advance in the state of the art. For reference, a 60% classifier improves the guessing probability of a 12-image HIP from 1/4096 to 1/459. The current literature suggests machine classifiers can score above 80% accuracy on this task [1]. Therefore, Asirra is no longer considered safe from attack. This contest aims to benchmark the latest computer vision and deep learning approaches to this problem.

《猫狗分类》是Kaggle平台上的一项竞赛，要求参赛者开发算法以判别图像中包含的动物为狗还是猫，其训练存档包含25000张猫狗图像。Web服务通常会通过一类验证机制进行防护：这类验证对人类而言易于完成，但对计算机却极具挑战。这类验证机制常被称为验证码（CAPTCHA，全称为Completely Automated Public Turing test to tell Computers and Humans Apart）或人机交互验证（Human Interactive Proof，简称HIP）。HIP可应用于诸多场景，例如减少电子邮件与博客垃圾评论，以及防止针对网站密码的暴力破解攻击。Asirra（全称Animal Species Image Recognition for Restricting Access，即限制访问的动物图像识别系统）是一类HIP，其运行逻辑为要求用户识别猫狗的照片。该任务对计算机而言难度颇高，但研究表明人类可以快速且准确地完成，甚至不少用户认为此过程颇具乐趣。Asirra的独特之处在于其与全球最大的流浪宠物领养平台Petfinder.com达成合作，该平台为微软研究院（Microsoft Research）提供了超过300万张猫狗图像，这些图像均由美国数千家动物收容所的工作人员手动标注分类。Kaggle有幸能够推出该数据集的子集以供爱好者与研究人员使用。尽管随机猜测是最基础的攻击方式，但各类图像识别技术可使攻击者实现优于随机猜测的识别准确率。该图像数据库涵盖了极为丰富的多样性——包括多样的背景、拍摄角度、动物姿态、光照条件等，这使得精准的自动分类任务极具挑战。在多年前开展的一项非正式调研中，计算机视觉领域专家曾指出，若未在当前技术水平上取得重大突破，开发准确率超过60%的分类器将极具难度。作为参考，准确率为60%的分类器可将12张图像组成的HIP任务的猜中概率从1/4096提升至1/459。当前的学术文献表明，机器学习分类器在该任务上的准确率已可突破80%[1]。因此，Asirra已不再被视为可抵御攻击的安全验证机制。本竞赛旨在为针对该任务的最新计算机视觉与深度学习方法提供性能基准测试平台。

搜集汇总

背景与挑战

背景概述

该数据集是Kaggle竞赛'Dogs vs. Cats'的一部分，包含25,000张猫和狗的图片，用于训练算法进行图像分类。它源自Asirra CAPTCHA项目，数据由Petfinder.com提供，旨在评估计算机视觉和深度学习方法的性能，当前最佳准确率已超过80%。