Paper Explanation: Binarized Neural Networks: Training Neural Networks with Weights and Activations Constrained to +1 or −1

Motivation What if you want to do some real-time face detection/recognition using a deep learning system running on a pair of glasses? What if you want your alarm clock to be able to record and analyze your sleep and conditions around you and come up with the most optimal way of waking you up each … Continue reading Paper Explanation: Binarized Neural Networks: Training Neural Networks with Weights and Activations Constrained to +1 or −1

Paper Explanation – Deep Residual Learning for Image Recognition (ResNet)

This paper is the outcome when Microsoft finally released the beast! The ResNet "slayed" everything, and won not one, not two, but five competitions; ILSVRC 2015 Image Classification, Detection and Localization, and COCO 2015 detection and segmentation. Problems the Paper Addressed The paper analysed what was causing the accuracy of deeper networks to drop as … Continue reading Paper Explanation – Deep Residual Learning for Image Recognition (ResNet)

Paper Explanation: Going Deeper with Convolutions (GoogLeNet)

This is the only paper I know of that references a meme! Not only this but this model also became the state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). Problems the Paper Addressed To create a deep network with high accuracy while keeping computation low. Google … Continue reading Paper Explanation: Going Deeper with Convolutions (GoogLeNet)

Paper Explanation: Very Deep Covolutional Networks for Large-Scale Image Recognition (VGGNet)

This is probably the most simple looking and straightforward network ever. Simple yet powerful; wining the ImageNet 2014 Localisation competition and coming second in the Classification track! Problems the Paper Addressed To show that making a network deeper improves its accuracy and also multiple small filters are better than a single large filter when both … Continue reading Paper Explanation: Very Deep Covolutional Networks for Large-Scale Image Recognition (VGGNet)

Paper Explanation: Faster R-CNN Towards Real-Time Object Detection with Region Proposal Networks

What Led to Faster R-CNN? Even though networks like Fast R-CNN achieve a really high accuracy, they are very slow to be of practical use in real time. The reason for such slow speeds is the region proposal step in the architecture! Algorithms, like Selective Search (used in Fast R-CNN) take around 2 seconds per … Continue reading Paper Explanation: Faster R-CNN Towards Real-Time Object Detection with Region Proposal Networks

Paper Explanation: Fast R-CNN

Called Fast R-CNN because it's comparatively fast to train and test. Why Fast R-CNN? Even though R-CNN had achieved state of the art performance on object detection it had many problems: Slow at test-time due to independent forward passes of the CNN for each region proposal. The CNN doesn't get trained during the training of the … Continue reading Paper Explanation: Fast R-CNN

Paper Explanation: Rich feature hierarchies for accurate object detection and semantic segmentation (R-CNN)

To what extent do the CNN classification generalise to object detection? Object detection is the task of finding the different objects in an image and classifying them (as seen in the image above). This paper is the first to show that a CNN can lead to dramatically higher object detection performance Let’s now take a moment … Continue reading Paper Explanation: Rich feature hierarchies for accurate object detection and semantic segmentation (R-CNN)