DINO - Emerging Properties in Self-Supervised Vision Transformers
May 24, 2021 • 9 min read
Unsupervised visual feature learning using knowledge distillation and transformers
CLIP - Contrastive Language-Image Pre-training
February 26, 2021 • 9 min read
Contrastive learning for unified vision-language representations in a shared embedding space
Vision Transformer - An Image is Worth 16x16 Words
October 22, 2020 • 6 min read
Google shows how treating image patches as tokens can revolutionize computer vision
The Receptive Field in Convolutional Neural Networks
October 10, 2018 • 5 min read
Why do architectures use 3x3 filters? It is because of something called Receptive Fields.
SENet - Squeeze and Excitation Networks
September 17, 2017 • 6 min read
Introducing channel attention to improve the performance of image classification tasks
MobileNet v1 - Efficient Convolutional Neural Networks
April 17, 2017 • 6 min read
Efficient convolutional neural networks for mobile vision applications
Depthwise Separable Convolutions
August 25, 2016 • 3 min read
Same results as standard convolutions with only a fraction of the computational cost. Explore the tricks behind MobileNet and efficient CNNs
DenseNet - Densely Connected Convolutional Networks
August 25, 2016 • 6 min read
Connecting each layer to every other layer to maximize information flow and efficiency
