Stanford-CV华人教授李飞飞写给她学生的一封信，如何做好研究以及写好PAPER，受益匪浅
Stanford-CV华人教授李飞飞写给她学生的一封信，如何做好研究以及写好PAPER，受益匪浅
李飞飞是斯坦福大学计算机视觉领域的牛人。
De-mystifying Good Research and Good Papers
By Fei-Fei Li, 2009.03.01
Please remember this:
1000+ computer vision papers get published every year!
Only 5-10 are worth reading and remembering!
Since many of you are writing your papers now, I thought that I'd share these thoughts with you. I probably have said all these at various points during our group and individual meetings. But as I continue my AC reviews these days (that's 70 papers and 200+ reviews -- between me and my AC partner), these following points just keep coming up. Not enough people conduct first class research. And not enough people write good papers.
- Every research project and every paper should be conducted and written with one singular purpose: *to genuinely advance the field of computer vision*. So when you conceptualize and carry out your work, you need to be constantly asking yourself this question in the most critical way you could – “Would my work define or reshape xxx (problem, field, technique) in the future?” This means publishing papers is NOT about "this has not been published or written before, let me do it", nor is it about “let me find an arcane little problem that can get me an easy poster”. It's about "if I do this, I could offer a better solution to this important problem," or “if I do this, I could add a genuinely new and important piece of knowledge to the field.” You should always conduct research with the goal that it could be directly used by many people (or industry). In other words, your research topic should have many ‘customers’, and your solution would be the one they want to use.
- A good research project is not about the past (i.e. obtaining a higher performance than the previous N papers). It's about the future (i.e. inspiring N future papers to follow and cite you, N->\inf).
- A CVPR'09 submission with a Caltech101 performance of 95% received 444 (3 weakly rejects) this year, and will be rejected. This is by far the highest performance I've seen for Caltech101. So why is this paper rejected? Because it doesn't teach us anything, and no one will likely be using it for anything. It uses a known technique (at least for many people already) with super tweaked parameters custom-made for the dataset that is no longer a good reflection of real-world image data. It uses a BoW representation without object level understanding. All reviewers (from very different angles) asked the same question "what do we learn from your method?" And the only sensible answer I could come up with is that Caltech101 is no longer a good dataset.
- Einstein used to say: everything should be made as simple as possible, but not simpler. Your method/algorithm should be the most simple, coherent and principled one you could think of for solving this problem. Computer vision research, like many other areas of engineering and science research, is about problems, not equations. No one appreciates a complicated graphical model with super fancy inference techniques that essentially achieves the same result as a simple SVM -- unless it offers deeper understanding of your data that no other simpler methods could offer. A method in which you have to manually tune many parameters is not considered principled or coherent.
- This might sound corny, but it is true. You're PhD students in one of the best universities in the world. This means you embody the highest level of intellectualism of humanity today. This means you are NOT a technician and you are NOT a coding monkey. When you write your paper, you communicate and . That's what a paper is about. This is how you should approach your writing. You need to feel proud of your paper not just for the day or week it is finished, but many for many years to come.
- Set a high goal for yourself – the truth is, you can achieve it as long as you put your heart in it! When you think of your paper, ask yourself this question: Is this going to be among the 10 papers of 2009 that people will remember in computer vision? If not, why not? The truth is only 10+/-epsilon gets remembered every year. Most of the papers are just meaningless publication games. A long string of mediocre papers on your resume can at best get you a Google software engineer job (if at all – 2009.03 update: no, Google doesn’t hire PhD for this anymore). A couple of seminal papers can get you a faculty job in a top university. This is the truth that most graduate students don't know, or don't have a chance to know.
- Review process is highly random. But there is one golden rule that withstands the test of time and randomness -- badly written papers get bad reviews. Period. It doesn't matter if the idea is good, result is good, citations are good. Not at all. Writing is critical -- and this is ironic because engineers are the worst trained writers among all disciplines in a university. You need to discipline yourself: leave time for writing, think deeply about writing, and write it over and over again till it's as polished as you can think of.
- Last but not the least, please remember this rule: important problem (inspiring idea) + solid and novel theory + convincing and analytical experiments + good writing = seminal research + excellent paper. If any of these ingredients is weak, your paper, hence reviewer scores, would suffer.
解开好的研究和好的论文
作者
：
李菲菲，2009.03.01 请记住： 每年有超过1000篇计算机视觉文章发表！
只有5-10个值得阅读和记忆！
既然你们中的很多人现在正在写论文，我以为我会和你分享这些想法。我可能已经在我们小组和个人会议上的各个地方说过这些了。但是现在我继续我的AC评论（这是70篇论文和200多条评论 - 在我和我的AC合作伙伴之间），以下几点不断出现。没有足够的人进行一流的研究。没有足够的人写好文件。
- 每一个研究项目和每一篇论文都应该以一个奇异的目的进行和编写：*真正推进计算机视觉领域*。所以，当你构想和开展工作的时候，你需要不断地以最关键的方式问自己这个问题 - “我的工作将来会定义或重塑xxx（问题，领域，技术）吗？”这意味着发布论文不是关于“这个以前没有发表过或者没有写过，让我去做”，也不是关于“让我找到一个能让我轻松搞定的奥秘小问题”。这是关于“如果我这样做，我可以提供一个更好的解决这个重要的问题”，或者“如果我这样做，我可以添加一个真正的新的和重要的知识的一块领域。“你应该总是进行研究，以便可以被许多人（或工业）直接使用的目标。换句话说，你的研究课题应该有很多“客户”，你的解决方案将是他们想要使用的。
- 一个好的研究项目不是过去的（即获得比以前的N篇论文更高的性能）。这是关于未来的（即启发N篇未来论文，并引用你，N - > \ inf）。
- CVPR'09提交的Caltech101表现为95％，今年共收到444个（3个弱拒绝），将被拒绝。这是迄今为止我所见到的Caltech101的最高性能。那么为什么这个文件被拒绝？因为它没有教我们什么，也没有人会用它来做任何事情。它使用已知的技术（至少对于许多人来说）为数据集定制的超级调整的参数，这已经不再是真实图像数据的良好反映。它使用没有对象级别理解的BoW表示。所有评论者（从不同角度）都提出了同样的问题：“我们从你的方法中学到了什么？” 我能想出的唯一明智的答案是Caltech101不再是一个好的数据集。
- 爱因斯坦曾经说过：一切都应该尽可能地简单，但并不简单。你的方法/算法应该是你能想到解决这个问题的最简单，一致和最原则的方法。计算机视觉研究与其他许多工程和科学研究领域一样，都是关于问题的，而不是方程式。没有人理解复杂的超级花式推理技术的图形模型，它基本上可以达到与简单的SVM相同的结果 - 除非它提供了更深入的数据理解，而没有其他更简单的方法可以提供。您必须手动调整许多参数的方法不被视为原则性或一致性。
这可能听起来很古怪，但这是事实。你是世界上最好的大学之一的博士生。这意味着你体现了当今人类最高层的智慧主义。这意味着你不是技术人员，而且你不是一个编码猴子。当你写你的文件，你沟通和。这是一篇论文。这就是你应该如何处理你的写作。你需要为你的论文感到自豪，不仅仅是一天或一周的结束，而是很多很多年。
- 为自己设定一个高目标 - 事实是，只要你放心，就可以实现目标！当你想到你的论文的时候，问自己这个问题：这是否会成为2009年计算机视觉领域的10篇文章之一？如果没有，为什么不呢？事实是每年只有10 +/- epsilon记住。大多数报纸只是无意义的刊物游戏。简历中的一连串平庸的论文最多只能让你成为一名Google软件工程师（如果有的话 - 2009.03更新：不，Google不会再雇用博士学位）。一些开创性的论文可以让你在顶尖大学任教。这是大多数研究生不知道，或没有机会知道的事实。
- 审查过程是高度随机的。但是有一条经得起时间和随机性考验的金科玉律 - 写得不好的论文得到了不好的评论。期。这个想法不错，结果不错，引用是好的。一点也不。写作是至关重要的 - 这是讽刺的，因为工程师是大学所有学科中训练最差的作家。你需要自我约束：留下时间写作，深入思考写作，并一遍又一遍地写下来，直到它被认为是精致的。
- 最后但并非最不重要的，请记住这个规则：重要的问题（鼓舞人心的想法）+坚实和新颖的理论+令人信服的分析实验+好的写作=开创性的研究+出色的论文。如果这些成分中的任何一个都很弱，那么你的论文，因此评论者的分数就会受到影响。