AI Component Benchmark

Please click HERE to view "The Teamwork Development Guide" , if you're a member of AIBench project.

To Do List (10/15)

#	Name	Algorithm	Dataset	Tensorflow	PyTorch
1	Image Classification	ResNet20/ResNet32	CIFAR-10	✔️	❌
2	Image Generation	WassersteinGAN	LSUN	❌	✔️
3	Text2Text	Attention	WMT English-German	✔️	✔️
4	Image2Text	InceptionV3+LSTM	MS COCO2014	✔️	❌
5	Image2Image	CycleGAN	Cityscapes	❌	✔️
6	Speech2Text	Deep Speech 2	LibriSpeech	❌	❌
7	Face Embedding	facenet	CASIA-WebFace/VGGFace2	✔️	❌
8	Object Detection	Faster R-CNN	Pascal VOC2007/MS COCO2014	✔️	✔️
9	Recommendation	Probabilistic MF	MovieLens ml-100k/GroupLens	➖	➖
10	PageRank	PageRank	Google Web Graph	➖	➖
11	Graph Model	LDA	Wikipedia English articles	➖	➖
12	Clustering	K-Means	Facebook Social Network	➖	➖
13	Classification	Native Bayes Classification	Amazon Movie Review	➖	➖
14	Feature Exaction	SIFT	ImageNet	➖	➖
15	Search Engine Indexing	Inverted Index	Wikipedia English articles	➖	➖

Each component benchmark is specified with a problem statement, one or more dataset, algorithms, involved data motifs, implementations and their contributors.

1. Image classification

Workloads type: AI
Application domains:
Dataset: Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M. S.; Berg, A. C.; Fei-Fei, L. (2015). ImageNet Large Scale Visual Recognition Challenge, International Journal of Computer Vision (IJCV).
Algorithm: He, K.; Zhang, X.; Ren, S; Sun, J. (2015), 'Deep Residual Learning for Image Recognition', CoRR abs/1512.03385.
Involved data motifs:
Software stacks:
Implementation Contributors:

2. Image generation

Workloads type: AI
Application domains:
Dataset: Fisher Yu, Yinda Zhang, Shuran Song, Ari Seff, and Jianxiong Xiao. LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop. Corr, abs/1506.03365, 2015.
Algorithm: Arjovsky, Martin, Chintala, Soumith, and Bottou, L´eon. Wasserstein gan. arXiv preprint arXiv:1701.07875, 2017.
Involved data motifs:
Software stacks:
Implementation Contributors:
References:

3. Text-to-Text Translation

Workloads type: AI
Application domains:
Dataset: WMT English-German from Bojar, O.; Buck, C.; Federmann, C.; Haddow, B.; Koehn, P.; Monz, C.; Post, M.; Specia, L., ed. (2014), Proceedings of the Ninth Workshop on Statistical Machine Translation, Association for Computational Linguistics, Baltimore, Maryland, USA.
Algorithm: Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, L.; Polosukhin, I. (2017), 'Attention Is All You Need', CoRR abs/1706.03762.
Involved data motifs:
Software stacks:
Implementation Contributors:

4. Image-to-Text

Workloads type: AI
Application domains:
Dataset: MS COCO dataset, http://cocodataset.org/
Algorithm: "Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge." Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan. IEEE transactions on pattern analysis and machine intelligence (2016).
Involved data motifs:
Software stacks:
Implementation Contributors:

5. Image-to-Image

Workloads type: AI
Application domains:
Dataset: M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele. The cityscapes dataset for semantic urban scene understanding. In CVPR, 2016
Algorithm: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Involved data motifs:
Software stacks:
Implementation Contributors:

6. Speech-to-Text

Workloads type: AI
Application domains:
Dataset: Panayotov, V.; Chen, G.; Povey, D.; Khudanpur, S. (2015), Librispeech: An ASR corpus based on public domain audio books, in '2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)', pp. 5206-5210.
Algorithm: Amodei, D.; Anubhai, R.; Battenberg, E.; Case, C.; Casper, J.; Catanzaro, B.; Chen, J.; Chrzanowski, M.; Coates, A.; Diamos, G.; Elsen, E.; Engel, J.; Fan, L.; Fougner, C.; Han, T.; Hannun, A. Y.; Jun, B.; LeGresley, P.; Lin, L.; Narang, S.; Ng, A. Y.; Ozair, S.; Prenger, R.; Raiman, J.; Satheesh, S.; Seetapun, D.; Sengupta, S.; Wang, Y.; Wang, Z.; Wang, C.; Xiao, B.; Yogatama, D.; Zhan, J.; Zhu, Z. (2015), 'Deep Speech 2: End-to-End Speech Recognition in English and Mandarin', CoRR abs/1512.02595.
Involved data motifs:
Software stacks:
Implementation Contributors:

7. Face embedding

Workloads type: AI
Application domains:
Dataset: G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Massachusetts, Amherst, October 2007. 5
Algorithm: FaceNet: A Unified Embedding for Face Recognition and Clustering
Involved data motifs:
Software stacks:
Implementation Contributors:

8. Object detection

Workloads type: AI
Application domains:
Dataset: Lin, T.-Y.; Maire, M.; Belongie, S. J.; Bourdev, L. D.; Girshick, R. B.; Hays, J.; Perona, P.; Ramanan, D.; Dollбr, P.; Zitnick, C. L. (2014), 'Microsoft COCO: Common Objects in Context', CoRR abs/1405.0312.
Algorithm: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Involved data motifs:
Software stacks:
Implementation Contributors:

9. Recommendation

Workloads type: AI
Application domains:
Dataset: Harper, F. M.; Konstan, J. A. (2015), 'The MovieLens Datasets: History and Context', ACM Trans. Interact. Intell. Syst. 5(4), 19:1--19:19.
Algorithm: Koren, Y., Bell, R.M., Volinsky, C. Matrix factorization techniques for recommender systems. IEEE Computer 42(8), 30–37 (2009)
Involved data motifs:
Software stacks:
Implementation Contributors:

10. PageRank

Workloads type: Graph Analytics
Application domains:
Dataset: Google web graph. http://snap.stanford.edu/data/web-Google.htm
Algorithm: L. Page, S. Brin, R. Motwani, and T. Winograd. The pagerank citation ranking: Bringing order to the web. Technical report, Stanford University, Stanford, CA, 1998. 17, 18, 88
Involved data motifs:
Software stacks:
Implementation Contributors:

11. Graph Model

Workloads type: Graph Analytics
Application domains:
Dataset: Wikipedia English articles. https://dumps.wikimedia.org/
Algorithm: D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent dirichlet allocation. the Journal of machine Learning research, 3:993–1022, 2003.
Involved data motifs:
Software stacks:
Implementation Contributors:

12. Clustering

Workloads type: Big Data
Application domains:
Dataset: Facebook social network. http://snap.stanford.edu/data/egonets-Facebook.html
Algorithm: Krishna, K., Murty, M. N. (1999). Genetic K-means algorithm. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 29(3), 433-439.
Involved data motifs:
Software stacks:
Implementation Contributors:

13. Classification

Workloads type:
Application domains:
Dataset: Amazon movie review. http://snap.stanford.edu/data/web-Movies.html
Algorithm: Rish, I. (2001, August). An empirical study of the naive Bayes classifier. In IJCAI 2001 workshop on empirical methods in artificial intelligence (Vol. 3, No. 22, pp. 41-46). New York: IBM.
Involved data motifs:
Software stacks:
Implementation Contributors:

14. Feature Exaction

Workloads type:
Application domains:
Dataset: ImageNet. http://www.image-net.org
Algorithm: Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2), 91-110.
Involved data motifs:
Software stacks:
Implementation Contributors:

15. Search Engine Indexing

Workloads type:
Application domains:
Dataset: Wikipedia English articles. https://dumps.wikimedia.org/
Algorithm: Black, Paul E., inverted index, Dictionary of Algorithms and Data Structures, U.S. National Institute of Standards and Technology Oct 2006. Verified Dec 2006.
Involved data motifs:
Software stacks:
Implementation Contributors:

Others

Dual Learning

GBDT

Learning to Rank

Tranditional Machine Learning

Transformer

Social Network

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

paper view

tianshuh / AIBench