There are currently two broads axis of research in Deep Learning: finding better architectures, or finding better losses to train them. Since AlexNet (Kriwhevsky et al.), Convolutional Neural Network is the main architecture used in Computer Vision. Through convolutions, with its efficient patch prior, many visual tasks were unlocked.
Many variations of AlexNet were invented, but if we were to name only one, it would be the ResNet (He et al.) and its residual shortcut.
I review in this article, papers published at CVPR 2020 about Continual Learning. If you think I made a mistake or missed an important paper, please tell me!
Many papers this year in Continual Learning were about few-shot learning. Besides the CVPR papers I’ll present, there is also a workshop paper (Cognitively-Inspired Model for Incremental Learning Using a Few Examples, Ayub et al. CVPR Workshop 2020) and an arXiv (Defining Benchmarks for Continual Few-Shot Learning, Antoniou et al. arxiv:2004.11967).
Authors: Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, Yihong Gong
Tao et al. propose in this…
The hallmark of human intelligence is the capacity to learn. Everyday we learn new concepts, and more importantly we are capable of remembering what we learn. It would be very hard to improve ourselves without this capacity. Can our algorithms do the same?
The recent deep learning hype aims to reach the Artificial General Intelligence (AGI): an AI that would express (supra-)human-like intelligence. Unfortunately current deep learning models are flawed in many ways: one of them is that they are unable to learn continuously as human does through years of schooling, and so on.
Regardless of the far away goal…
Those notes are based on the research paper “ On Calibration of Modern Neural Networks” by (Guo et al, 2017.).
Very large and deep models, as ResNet, are far more accurate than their older counterparts, as LeNet, on computer vision datasets such as CIFAR100. However while they are better at classifying images, we are less confident in their own confidence!
Most neural networks for classification uses as last activation a softmax: it produces a distribution of probabilities for each target (cat, dog, boat, etc.). These probabilities sum to one. We may expect that if for a given image, our model…
A few months ago, NATO organized an innovation challenge that posed this very scenario and these very questions. We decided to take on the challenge with the goal of finding innovative solutions in the areas of data filtering/fusing, visualization, and predictive analytics.
For those who don’t know, NATO is an intergovernmental military alliance between 29 North American and European countries. It constitutes a system of collective defense whereby its independent member states agree to mutual defense in response to an attack by any external party.
NATO did not provide any data for the challenge, so we had to find it…
Imagine you’re in a landlocked country, and an infection has spread. The government has fallen, and rebels are roaming the country. If you’re the armed forces in this scenario, how do you make decisions in this environment? How can you fully understand the situation at hand?
A few weeks ago, NATO organized an innovation challenge that posed this very scenario and these very questions. We decided to take on the challenge with the goal of finding innovative solutions in the areas of data filtering/fusing, visualization, and predictive analytics.
For those who don’t know, NATO is an intergovernmental military alliance between…
Many CNN architectures have been developed to attain the best accuracy on ImageNet. Computing power is not limited for this competition, why bother?
However you may want to run your model on an old laptop, maybe without GPU, or even on your mobile phone. Let’s see three CNN architectures that are efficient while sacrificing few accuracy performance.
Arxiv link: (Howard et al, 2017)
MobileNet uses depthwise separable convolutions. This convolution block was at first introduced by Xception. A depthwise separable convolution is made of two operations: a depthwise convolution and a pointwise convolution.
A standard convolution works on the spatial…