When and how CNNs generalize

02/22/2022

When and how CNNs generalize to out-of-distribution category-viewpoint combinations

Spandan Madan and Xavier Boix discuss their latest research recently published in Nature Machine Intelligence.

Reach out to us now to explore your unique training requirements and uncover our potential to assist you.

Bono, S., Madan, S., Grover, I., Yasueda, M., Breazeal, C., Pfister, H., & Kreiman, G. (2025). The Indoor-Training Effect: unexpected gains from distribution shifts in the transition function. AAAI. https://drive.google.com/file/d/1WSpHklye2Edkm0c_SBPltVCoM081Pj7l/view?usp=sharing
Madan, S., Li, Y., Zhang, M., Pfister, H., & Kreiman, G. (2024). Improving generalization by mimicking the human visual diet. BioRxiv, 2206.07802. https://drive.google.com/file/d/17NhH3cw-cYB9pM2bOdnrkSUNlKR_KbWt/view?usp=sharing
Madan, S., Xiao, W., Cao, M., Pfister, H., Livingstone, M., & Kreiman, G. (2024). Benchmarking out-of-distribution generalization capabilities of DNN-based encoding models for the ventral visual cortex. NeurIPS. https://drive.google.com/file/d/1JlzUPI_5BQ1OmPj2e67ZXdv-YJorBWHZ/view?usp=sharing
Madan, S. (2024). Out-of-distribution generalization in biological and artificial intelligence [Harvard University]. https://drive.google.com/file/d/19_azuONFThFBpG4yxAr5KB_e0WBKUeug/view?usp=sharing
Zhang, M., Dellaferrera, G., Sikarwar, A., Armendariz, M., Mudrik, N., Agrawal, P., Madan, S., Barbu, A., Yang, H., Kumar, T., Sadwani, M., Dellaferrera, S., Pizzochero, M., Pfister, H., & Kreiman, G. (2022). Human or Machine? Turing Tests for Vision and Language. ArXiv, 2211.13087. https://drive.google.com/file/d/1WhrlNJP9kxS3YeCJYEjbvuz6nRd0lNmG/view?usp=sharing
Bomatter, P., Zhang, M., Karev, D., Madan, S., Tseng, C., & Kreiman, G. (2021). When pigs fly: contextual reasoning in synthetic and natural scenes. International Conference on Computer Vision (ICCV). https://drive.google.com/file/d/11nUVQHh4vucGpmokq-RD0Fl9fJOAYFWu/view?usp=sharing