---
title: "FiLM: Visual Reasoning with a General — Perez 2017"
description: "Standard visual question answering models often fail on CLEVR, a benchmark of questions that need multi-step reasoning about rendered scenes."
authors: ["Ethan Perez", "Florian Strub", "Harm de Vries", "Vincent Dumoulin", "Aaron Courville"]
year: 2017
venue: "arXiv:1709.07871"
source: "https://arxiv.org/abs/1709.07871"
doi: "10.48550/arxiv.1709.07871"
arxiv: "1709.07871"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/perez-2017-film-visual-reasoning-general-conditioning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/perez-2017-film-visual-reasoning-general-conditioning/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/) / FiLM: Visual Reasoning with a General Conditioning Layer

# FiLM: Visual Reasoning with a General Conditioning Layer

**Authors:** [Ethan Perez](https://md.research.elamur.ai/free/en/authors/ethan-perez/), Florian Strub, Harm de Vries, Vincent Dumoulin, [Aaron Courville](https://md.research.elamur.ai/free/en/authors/aaron-courville/) · **Year:** 2017 · **Venue:** arXiv:1709.07871 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1709.07871) · [PDF](https://arxiv.org/pdf/1709.07871) · [DOI 10.48550/arxiv.1709.07871](https://doi.org/10.48550/arxiv.1709.07871) · [arXiv 1709.07871](https://arxiv.org/abs/1709.07871) · [OpenAlex](https://openalex.org/W2734498959)

**Citations:** 184 citations (openalex-snapshot · 2026-10-14) · [164](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Standard visual question answering models often fail on CLEVR, a benchmark of questions that need multi-step reasoning about rendered scenes. They tend to exploit dataset biases instead. The authors avoid hard-coding reasoning structure into the architecture. They propose FiLM (Feature-wise Linear Modulation), a generic conditioning layer in which one network predicts a scale (γ) and a shift (β) for every feature map of another network. In their model, a GRU reads the question and outputs these parameters for several residual blocks of an image CNN, so language steers visual processing directly. The model is trained end-to-end only on CLEVR image-question-answer triplets, and it roughly halves the previous best error on CLEVR. Ablations show that the gains survive many design changes and do not require placing the affine transformation right after normalization. On CLEVR-CoGenT, FiLM adapts well from little fine-tuning data, and arithmetic on its predicted parameters enables some zero-shot generalization. The work suggests that a cheap, general-purpose conditioning mechanism can rival architectures built specifically for reasoning.

## Key points
- **Architecture:**
  - The FiLM generator is a GRU with 4096 hidden units over 200-dimensional word embeddings.
  - The visual pipeline has 4 FiLM-ed ResBlocks with 128 feature maps each.
  - Image features come either from a CNN trained from scratch or from a frozen ResNet-101 conv4 extractor pre-trained on ImageNet.
- **Efficiency:** FiLM needs only two parameters per modulated feature map, and its cost does not grow with image resolution.
- **Relation to prior methods:** FiLM generalizes Conditional Normalization variants such as Conditional Instance Norm, Adaptive Instance Norm, Dynamic Layer Norm and Conditional Batch Norm. The experiments indicate that the normalization step is not essential.
- **Sample efficiency on CLEVR-CoGenT:** FiLM reaches the prior state of the art with one third of the fine-tuning data. Even so, fine-tuning leaves the model prone to losing much of what it had previously learned.
- **Zero-shot method:** Questions are combined linearly in (γ, β) space, analogous to word-embedding analogies.
  - Training on condition A and testing zero-shot on B gives a 3.2% overall accuracy gain.
  - The method applies to about 1/3 of the questions in B, where accuracy rises from 71.5% to 80.7%.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Other](https://md.research.elamur.ai/free/en/shelves/other/)

## Cited by

Cited by

164 papers of our library cite it (of the 140673 whose bibliographies we read); 10 of them have a page here, 154 not yet.

- [Seamless: Multilingual Expressive and Streaming Speech Translation](https://md.research.elamur.ai/free/en/papers/communication-2023-seamless-multilingual-expressive-streaming-speech/)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://md.research.elamur.ai/free/en/papers/kim-2021-vilt-vision-language-transformer-convolution/)
- [Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning](https://md.research.elamur.ai/free/en/papers/lu-2021-inter-gps-interpretable-geometry-problem/)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://md.research.elamur.ai/free/en/papers/mahabadi-2021-parameter-efficient-multi-task-fine/)
- [A Corpus for Reasoning About Natural Language Grounded in Photographs (NLVR2)](https://md.research.elamur.ai/free/en/papers/suhr-2019-corpus-reasoning-natural-language-grounded/)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://md.research.elamur.ai/free/en/papers/tan-2019-lxmert-learning-cross-modality-encoder/)
- [Dynamic Routing Transformer Network for Multimodal Sarcasm Detection](https://md.research.elamur.ai/free/en/papers/tian-2023-dynamic-routing-transformer-network-multimodal/)
- [基于大模型的具身智能系统综述](https://md.research.elamur.ai/free/en/papers/wang-2025-embodied-intelligence-systems/)
- [Big Five Personality Prediction through Emotion-Conditioned Representations and Learnable Psycholinguistic Mapping](https://md.research.elamur.ai/free/en/papers/zangari-2026-big-five-personality-prediction-through/)
- [SoundStream: An End-to-End Neural Audio Codec](https://md.research.elamur.ai/free/en/papers/zeghidour-2021-soundstream-end-end-neural-audio/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{perez2017film,
  title = {{FiLM: Visual Reasoning with a General Conditioning Layer}},
  author = {Perez, Ethan and Strub, Florian and Vries, Harm de and Dumoulin, Vincent and Courville, Aaron},
  year = {2017},
  doi = {10.48550/arxiv.1709.07871},
  eprint = {1709.07871},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1709.07871}
}
```

- [← previous Fast and Accurate Entity Recognition with Iterated Dilated Convolutions](https://md.research.elamur.ai/free/en/papers/strubell-2017-fast-accurate-entity-recognition-iterated/)
- [next → Findings of the 2017 Conference on Machine Translation (WMT17)](https://md.research.elamur.ai/free/en/papers/bojar-2017-findings-2017-conference-machine-translation/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/)

## References

38 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anderson, P.; He, X.; Buehler, C.; Teney, D.; Johnson, M.; Gould, S.; and Zhang, L. 2017. Bottom-up and top-down attention for image captioning and vqa. In VQA Workshop at CVPR. [find](https://scholar.google.com/scholar?q=Anderson%2C+P%2E%3B+He%2C+X%2E%3B+Buehler%2C+C%2E%3B+Teney%2C+D%2E%3B+Johnson%2C+M%2E%3B+Gould%2C+S%2E%3B+and+Zhang%2C+L%2E+2017%2E+Bottom%2Dup+and+top%2Ddown+attention+for+image+captioning+and+vqa%2E+In+VQA+Workshop+at+CVPR%2E)
2. Andreas, J.; Marcus, R.; Darrell, T.; and Klein, D. 2016a. Learning to compose neural networks for question answering. In NAACL. [find](https://scholar.google.com/scholar?q=Andreas%2C+J%2E%3B+Marcus%2C+R%2E%3B+Darrell%2C+T%2E%3B+and+Klein%2C+D%2E+2016a%2E+Learning+to+compose+neural+networks+for+question+answering%2E+In+NAACL%2E) [our card](https://md.research.elamur.ai/free/en/papers/andreas-2016-learning-compose-neural-networks-question/)
3. Andreas, J.; Rohrbach, M.; Darrell, T.; and Klein, D. 2016b. Neural module networks. In CVPR. [find](https://scholar.google.com/scholar?q=Andreas%2C+J%2E%3B+Rohrbach%2C+M%2E%3B+Darrell%2C+T%2E%3B+and+Klein%2C+D%2E+2016b%2E+Neural+module+networks%2E+In+CVPR%2E) [our card](https://md.research.elamur.ai/free/en/papers/andreas-2015-neural-module-networks/)
4. Antol, S.; Agrawal, A.; Lu, J.; Mitchell, M.; Batra, D.; Zitnick, C. L.; and Parikh, D. 2015. [find](https://scholar.google.com/scholar?q=Antol%2C+S%2E%3B+Agrawal%2C+A%2E%3B+Lu%2C+J%2E%3B+Mitchell%2C+M%2E%3B+Batra%2C+D%2E%3B+Zitnick%2C+C%2E+L%2E%3B+and+Parikh%2C+D%2E+2015%2E)
5. VQA: Visual Question Answering. In ICCV. Bordes, A.; Usunier, N.; Garcia-Duran, A.; Weston, J.; and Yakhnenko, O. 2013. Translating embeddings for modeling multi-relational data. In Burges, C. J. C.; Bottou, L.; Welling, M.; Ghahramani, Z.; and Weinberger, K. Q., eds., NIPS. Curran Associates, Inc.… [find](https://scholar.google.com/scholar?q=VQA%3A+Visual+Question+Answering%2E+In+ICCV%2E+Bordes%2C+A%2E%3B+Usunier%2C+N%2E%3B+Garcia%2DDuran%2C+A%2E%3B+Weston%2C+J%2E%3B+and+Yakhnenko%2C+O%2E+2013%2E+Translating+embeddings+for+modeling+multi%2Drelational+data%2E+In+Burges%2C+C%2E+J%2E+C%2E%3B+)
6. Dumoulin, V.; Shlens, J.; and Kudlur, M. 2017. A learned representation for artistic style. In ICLR. [find](https://scholar.google.com/scholar?q=Dumoulin%2C+V%2E%3B+Shlens%2C+J%2E%3B+and+Kudlur%2C+M%2E+2017%2E+A+learned+representation+for+artistic+style%2E+In+ICLR%2E)
7. Eigen, D.; Ranzato, M.; and Sutskever, I. 2014. Learning factored representations in a deep mixture of experts. In ICLR Workshops. [find](https://scholar.google.com/scholar?q=Eigen%2C+D%2E%3B+Ranzato%2C+M%2E%3B+and+Sutskever%2C+I%2E+2014%2E+Learning+factored+representations+in+a+deep+mixture+of+experts%2E+In+ICLR+Workshops%2E)
8. Gehring, J.; Auli, M.; Grangier, D.; Yarats, D.; and Dauphin, Y. N. 2017. Convolutional sequence to sequence learning. In ICML. [find](https://scholar.google.com/scholar?q=Gehring%2C+J%2E%3B+Auli%2C+M%2E%3B+Grangier%2C+D%2E%3B+Yarats%2C+D%2E%3B+and+Dauphin%2C+Y%2E+N%2E+2017%2E+Convolutional+sequence+to+sequence+learning%2E+In+ICML%2E) [our card](https://md.research.elamur.ai/free/en/papers/gehring-2017-convolutional-sequence-sequence-learning/)
9. Geman, D.; Geman, S.; Hallonquist, N.; and Younes, L. 2015. Visual turing test for computer vision systems. volume 112, 3618– 3623. National Acad Sciences. [find](https://scholar.google.com/scholar?q=Geman%2C+D%2E%3B+Geman%2C+S%2E%3B+Hallonquist%2C+N%2E%3B+and+Younes%2C+L%2E+2015%2E+Visual+turing+test+for+computer+vision+systems%2E+volume+112%2C+3618%E2%80%93+3623%2E+National+Acad+Sciences%2E)
10. Ghiasi, G.; Lee, H.; Kudlur, M.; Dumoulin, V.; and Shlens, J. 2017. Exploring the structure of a real-time, arbitrary neural artistic stylization network. CoRR abs/1705.06830. — [arXiv:1705.06830](https://arxiv.org/abs/1705.06830) [find](https://scholar.google.com/scholar?q=Ghiasi%2C+G%2E%3B+Lee%2C+H%2E%3B+Kudlur%2C+M%2E%3B+Dumoulin%2C+V%2E%3B+and+Shlens%2C+J%2E+2017%2E+Exploring+the+structure+of+a+real%2Dtime%2C+arbitrary+neural+artistic+stylization+network%2E+CoRR+abs%2F1705%2E06830%2E+%E2%80%94+%5BarXiv%3A1705%2E06830%5D%28htt)
11. Goyal, Y.; Khot, T.; Summers-Stay, D.; Batra, D.; and Parikh, D. 2017. Making the V in VQA matter: Elevating the role of image understanding in Visual Question Answering. In CVPR. [find](https://scholar.google.com/scholar?q=Goyal%2C+Y%2E%3B+Khot%2C+T%2E%3B+Summers%2DStay%2C+D%2E%3B+Batra%2C+D%2E%3B+and+Parikh%2C+D%2E+2017%2E+Making+the+V+in+VQA+matter%3A+Elevating+the+role+of+image+understanding+in+Visual+Question+Answering%2E+In+CVPR%2E) [our card](https://md.research.elamur.ai/free/en/papers/goyal-2016-making-v-vqa-matter-elevating/)
12. Guu, K.; Miller, J.; and Liang, P. 2015. Traversing knowledge graphs in vector space. In EMNLP. [find](https://scholar.google.com/scholar?q=Guu%2C+K%2E%3B+Miller%2C+J%2E%3B+and+Liang%2C+P%2E+2015%2E+Traversing+knowledge+graphs+in+vector+space%2E+In+EMNLP%2E)
13. Ha, D.; Dai, A.; and Le, Q. 2016. Hypernetworks. In ICLR. [find](https://scholar.google.com/scholar?q=Ha%2C+D%2E%3B+Dai%2C+A%2E%3B+and+Le%2C+Q%2E+2016%2E+Hypernetworks%2E+In+ICLR%2E)
14. He, K.; Zhang, X.; Ren, S.; and Sun, J. 2016. Deep residual learning for image recognition. In CVPR. [find](https://scholar.google.com/scholar?q=He%2C+K%2E%3B+Zhang%2C+X%2E%3B+Ren%2C+S%2E%3B+and+Sun%2C+J%2E+2016%2E+Deep+residual+learning+for+image+recognition%2E+In+CVPR%2E)
15. Hochreiter, S., and Schmidhuber, J. 1997. Long short-term memory. Neural Comput. 9(8):1735–1780. [find](https://scholar.google.com/scholar?q=Hochreiter%2C+S%2E%2C+and+Schmidhuber%2C+J%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+Comput%2E+9%288%29%3A1735%E2%80%931780%2E)
16. Hu, R.; Andreas, J.; Rohrbach, M.; Darrell, T.; and Saenko, K. 2017. Learning to reason: End-to-end module networks for visual question answering. In ICCV. [find](https://scholar.google.com/scholar?q=Hu%2C+R%2E%3B+Andreas%2C+J%2E%3B+Rohrbach%2C+M%2E%3B+Darrell%2C+T%2E%3B+and+Saenko%2C+K%2E+2017%2E+Learning+to+reason%3A+End%2Dto%2Dend+module+networks+for+visual+question+answering%2E+In+ICCV%2E)
17. Hu, J.; Shen, L.; and Sun, G. 2017. [find](https://scholar.google.com/scholar?q=Hu%2C+J%2E%3B+Shen%2C+L%2E%3B+and+Sun%2C+G%2E+2017%2E)
18. Squeeze-and-Excitation Networks. In ILSVRC 2017 Workshop at CVPR. [find](https://scholar.google.com/scholar?q=Squeeze%2Dand%2DExcitation+Networks%2E+In+ILSVRC+2017+Workshop+at+CVPR%2E)
19. Huang, X., and Belongie, S. 2017. Arbitrary style transfer in real-time with adaptive instance normalization. In ICCV. [find](https://scholar.google.com/scholar?q=Huang%2C+X%2E%2C+and+Belongie%2C+S%2E+2017%2E+Arbitrary+style+transfer+in+real%2Dtime+with+adaptive+instance+normalization%2E+In+ICCV%2E)
20. Ioffe, S., and Szegedy, C. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML. [find](https://scholar.google.com/scholar?q=Ioffe%2C+S%2E%2C+and+Szegedy%2C+C%2E+2015%2E+Batch+normalization%3A+Accelerating+deep+network+training+by+reducing+internal+covariate+shift%2E+In+ICML%2E)
21. Johnson, J.; Hariharan, B.; van der Maaten, L.; Fei-Fei, L.; Zitnick, C. L.; and Girshick, R. B. 2017a. CLEVR: A diagnostic dataset for compositional language and elementary visual reasoning. In CVPR. [find](https://scholar.google.com/scholar?q=Johnson%2C+J%2E%3B+Hariharan%2C+B%2E%3B+van+der+Maaten%2C+L%2E%3B+Fei%2DFei%2C+L%2E%3B+Zitnick%2C+C%2E+L%2E%3B+and+Girshick%2C+R%2E+B%2E+2017a%2E+CLEVR%3A+A+diagnostic+dataset+for+compositional+language+and+elementary+visual+reasoning%2E+In+CVPR%2E) [our card](https://md.research.elamur.ai/free/en/papers/johnson-2016-clevr-diagnostic-dataset-compositional-language/)
22. Johnson, J.; Hariharan, B.; van der Maaten, L.; Hoffman, J.; Li, F.; Zitnick, C. L.; and Girshick, R. B. 2017b. Inferring and executing programs for visual reasoning. In ICCV. [find](https://scholar.google.com/scholar?q=Johnson%2C+J%2E%3B+Hariharan%2C+B%2E%3B+van+der+Maaten%2C+L%2E%3B+Hoffman%2C+J%2E%3B+Li%2C+F%2E%3B+Zitnick%2C+C%2E+L%2E%3B+and+Girshick%2C+R%2E+B%2E+2017b%2E+Inferring+and+executing+programs+for+visual+reasoning%2E+In+ICCV%2E)
23. Jordan, M. I., and Jacobs, R. A. 1994. Hierarchical mixtures of experts and the em algorithm. Neural Comput. 6(2):181–214. [find](https://scholar.google.com/scholar?q=Jordan%2C+M%2E+I%2E%2C+and+Jacobs%2C+R%2E+A%2E+1994%2E+Hierarchical+mixtures+of+experts+and+the+em+algorithm%2E+Neural+Comput%2E+6%282%29%3A181%E2%80%93214%2E)
24. Kim, T.; Song, I.; and Bengio, Y. 2017. Dynamic layer normalization for adaptive neural acoustic modeling in speech recognition. In InterSpeech. [find](https://scholar.google.com/scholar?q=Kim%2C+T%2E%3B+Song%2C+I%2E%3B+and+Bengio%2C+Y%2E+2017%2E+Dynamic+layer+normalization+for+adaptive+neural+acoustic+modeling+in+speech+recognition%2E+In+InterSpeech%2E)
25. Kingma, D. P., and Ba, J. 2015. Adam: A method for stochastic optimization. In ICLR. [find](https://scholar.google.com/scholar?q=Kingma%2C+D%2E+P%2E%2C+and+Ba%2C+J%2E+2015%2E+Adam%3A+A+method+for+stochastic+optimization%2E+In+ICLR%2E)
26. Kirkpatrick, J.; Pascanu, R.; Rabinowitz, N.; Veness, J.; Desjardins, G.; Rusu, A. A.; Milan, K.; Quan, J.; Ramalho, T.; Grabska-Barwinska, A.; Hassabis, D.; Clopath, C.; Kumaran, D.; and Hadsell, R. 2017. Overcoming catastrophic forgetting in neural networks. National Academy of Sciences 114(13):35… [find](https://scholar.google.com/scholar?q=Kirkpatrick%2C+J%2E%3B+Pascanu%2C+R%2E%3B+Rabinowitz%2C+N%2E%3B+Veness%2C+J%2E%3B+Desjardins%2C+G%2E%3B+Rusu%2C+A%2E+A%2E%3B+Milan%2C+K%2E%3B+Quan%2C+J%2E%3B+Ramalho%2C+T%2E%3B+Grabska%2DBarwinska%2C+A%2E%3B+Hassabis%2C+D%2E%3B+Clopath%2C+C%2E%3B+Kumaran%2C+D%2E%3B+and+Hadsell%2C+R%2E+)
27. Lu, J.; Yang, J.; Batra, D.; and Parikh, D. 2016. Hierarchical question-image co-attention for visual question answering. In NIPS. [find](https://scholar.google.com/scholar?q=Lu%2C+J%2E%3B+Yang%2C+J%2E%3B+Batra%2C+D%2E%3B+and+Parikh%2C+D%2E+2016%2E+Hierarchical+question%2Dimage+co%2Dattention+for+visual+question+answering%2E+In+NIPS%2E)
28. Malinowski, M., and Fritz, M. 2014. A multi-world approach to question answering about real-world scenes based on uncertain input. In NIPS. [find](https://scholar.google.com/scholar?q=Malinowski%2C+M%2E%2C+and+Fritz%2C+M%2E+2014%2E+A+multi%2Dworld+approach+to+question+answering+about+real%2Dworld+scenes+based+on+uncertain+input%2E+In+NIPS%2E)
29. Malinowski, M.; Rohrbach, M.; and Fritz, M. 2015. Ask your neurons: A neural-based approach to answering questions about images. In ICCV. [find](https://scholar.google.com/scholar?q=Malinowski%2C+M%2E%3B+Rohrbach%2C+M%2E%3B+and+Fritz%2C+M%2E+2015%2E+Ask+your+neurons%3A+A+neural%2Dbased+approach+to+answering+questions+about+images%2E+In+ICCV%2E)
30. Mikolov, T.; Sutskever, I.; Chen, K.; Corrado, G. S.; and Dean, J. 2013. Distributed representations of words and phrases and their compositionality. In NIPS. [find](https://scholar.google.com/scholar?q=Mikolov%2C+T%2E%3B+Sutskever%2C+I%2E%3B+Chen%2C+K%2E%3B+Corrado%2C+G%2E+S%2E%3B+and+Dean%2C+J%2E+2013%2E+Distributed+representations+of+words+and+phrases+and+their+compositionality%2E+In+NIPS%2E)
31. Oh, J.; Singh, S.; Lee, H.; and Kholi, P. 2017. Zero-shot task generalization with multi-task deep reinforcement learning. In ICML. [find](https://scholar.google.com/scholar?q=Oh%2C+J%2E%3B+Singh%2C+S%2E%3B+Lee%2C+H%2E%3B+and+Kholi%2C+P%2E+2017%2E+Zero%2Dshot+task+generalization+with+multi%2Dtask+deep+reinforcement+learning%2E+In+ICML%2E)
32. Perez, E.; de Vries, H.; Strub, F.; Dumoulin, V.; and Courville, A. C. 2017. Learning visual reasoning without strong priors. In MLSLP Workshop at ICML. [find](https://scholar.google.com/scholar?q=Perez%2C+E%2E%3B+de+Vries%2C+H%2E%3B+Strub%2C+F%2E%3B+Dumoulin%2C+V%2E%3B+and+Courville%2C+A%2E+C%2E+2017%2E+Learning+visual+reasoning+without+strong+priors%2E+In+MLSLP+Workshop+at+ICML%2E)
33. Radford, A.; Metz, L.; and Chintala, S. 2016. Unsupervised representation learning with deep convolutional generative adversarial networks. In ICLR. [find](https://scholar.google.com/scholar?q=Radford%2C+A%2E%3B+Metz%2C+L%2E%3B+and+Chintala%2C+S%2E+2016%2E+Unsupervised+representation+learning+with+deep+convolutional+generative+adversarial+networks%2E+In+ICLR%2E) [our card](https://md.research.elamur.ai/free/en/papers/radford-2015-unsupervised-representation-learning-deep-convolutional/)
34. Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M. S.; Berg, A. C.; and Li, F. 2015. Imagenet large scale visual recognition challenge. IJCV 115(3):211–252. [find](https://scholar.google.com/scholar?q=Russakovsky%2C+O%2E%3B+Deng%2C+J%2E%3B+Su%2C+H%2E%3B+Krause%2C+J%2E%3B+Satheesh%2C+S%2E%3B+Ma%2C+S%2E%3B+Huang%2C+Z%2E%3B+Karpathy%2C+A%2E%3B+Khosla%2C+A%2E%3B+Bernstein%2C+M%2E+S%2E%3B+Berg%2C+A%2E+C%2E%3B+and+Li%2C+F%2E+2015%2E+Imagenet+large+scale+visual+recognition+challe) [our card](https://md.research.elamur.ai/free/en/papers/russakovsky-2014-imagenet-large-scale-visual-recognition/)
35. Santoro, A.; Raposo, D.; Barrett, D. G.; Malinowski, M.; Pascanu, R.; Battaglia, P.; and Lillicrap, T. 2017. A simple neural network module for relational reasoning. CoRR abs/1706.01427. [find](https://scholar.google.com/scholar?q=Santoro%2C+A%2E%3B+Raposo%2C+D%2E%3B+Barrett%2C+D%2E+G%2E%3B+Malinowski%2C+M%2E%3B+Pascanu%2C+R%2E%3B+Battaglia%2C+P%2E%3B+and+Lillicrap%2C+T%2E+2017%2E+A+simple+neural+network+module+for+relational+reasoning%2E+CoRR+abs%2F1706%2E01427%2E) [our card](https://md.research.elamur.ai/free/en/papers/santoro-2017-simple-neural-network-module-relational/)
36. Shazeer, N.; Mirhoseini, A.; Maziarz, K.; Davis, A.; Le, Q.; Hinton, G.; and Dean, J. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. In ICLR. van den Oord, A.; Dieleman, S.; Zen, H.; Simonyan, K.; Vinyals, O.; Graves, A.; Kalchbrenner, N.; Senior, A.; and Kavu… [find](https://scholar.google.com/scholar?q=Shazeer%2C+N%2E%3B+Mirhoseini%2C+A%2E%3B+Maziarz%2C+K%2E%3B+Davis%2C+A%2E%3B+Le%2C+Q%2E%3B+Hinton%2C+G%2E%3B+and+Dean%2C+J%2E+2017%2E+Outrageously+large+neural+networks%3A+The+sparsely%2Dgated+mixture%2Dof%2Dexperts+layer%2E+In+ICLR%2E+van+den+Oord%2C+A%2E%3B+) [our card](https://md.research.elamur.ai/free/en/papers/oord-2016-wavenet-generative-model-raw-audio/)
37. Watters, N.; Tacchetti, A.; Weber, T.; Pascanu, R.; Battaglia, P.; and Zoran, D. 2017. Visual interaction networks. CoRR abs/1706.01433. [find](https://scholar.google.com/scholar?q=Watters%2C+N%2E%3B+Tacchetti%2C+A%2E%3B+Weber%2C+T%2E%3B+Pascanu%2C+R%2E%3B+Battaglia%2C+P%2E%3B+and+Zoran%2C+D%2E+2017%2E+Visual+interaction+networks%2E+CoRR+abs%2F1706%2E01433%2E)
38. Yang, Z.; He, X.; Gao, J.; Deng, L.; and Smola, A. J. 2016. Stacked attention networks for image question answering. In CVPR. [find](https://scholar.google.com/scholar?q=Yang%2C+Z%2E%3B+He%2C+X%2E%3B+Gao%2C+J%2E%3B+Deng%2C+L%2E%3B+and+Smola%2C+A%2E+J%2E+2016%2E+Stacked+attention+networks+for+image+question+answering%2E+In+CVPR%2E)