Deep learning has achieved significant success for artificial intelligence (AI) in multiple fields, including computer vision, natural language processing, and acoustics. However, research in the AI field also shows that their performance in the wild is far from practical due to the lack of model efficiency and robustness towards open-world data and scenarios. Regarding model efficiency, in contrast to the ideal environment, it is impractical to train a huge neural network containing billions of parameters using a large-scale high-quality dataset and then deploy it to an edge device in practice. Meanwhile, considering model robustness, input data with noises frequently occur in open-world scenarios, which presents critical challenges for the building of robust AI systems in practice. Moreover, existing research presents that there is a trade-off between the robustness and accuracy of deep learning models, while in the context of efficient deep learning with limited resources, it is more challenging to achieve a better trade-off under the premise of satisfying efficiency. These complex demands have bought profound implications and explosion interests for research into the topic of this workshop, namely building practical AI with efficient and robust deep learning models. As far as we know, we are the first workshop to focus on practical deep learning in the wild, which is of great significance.

Important: The submission deadline has been extended to 21th Nov 2021 (AoE). (Submission Site)