In simple terms, dilated convolution is just a convolution applied to input with defined gaps. With this definitions, given our input is an 2D image, dilation rate k=1 is normal convolution and k=2 means skipping one pixel per input and k=4 means skipping 3 pixels. The best to see the figures below with the same k … Continue reading Dilated Convolution
What is Adversarial? Machine learning is everywhere and we are amazed with capabilities of these algorithms. However, they are not great and sometimes they behave so dumb. For instance, let's consider an image recognition model. This model induces really high empirical performance and it works great for normal images. Nevertheless, it might fail when you change … Continue reading Ensembling Against Adversarial Instances
Paper: https://arxiv.org/abs/1312.6199 This paper studies description of semantic information with higher level units of an network and blind spot of the network models againt adversarial instances. They illustrate the learned semantics inferring maximally activating instances per unit. They also interpret the effect of adversarial examples and their generalization on different network architectures and datasets. Findings … Continue reading Paper Notes: Intriguing Properties of Neural Networks
Suppose you have a problem that you like to tackle with machine learning and use the resulting system in a real-life project. I like to share my simple pathway for such purpose, in order to provide a basic guide to beginners and keep these things as a reminder to myself. These rules are tricky since even-thought … Continue reading Short guide to deploy Machine Learning
Selfies are everywhere. With different fun masks, poses and filters, it goes crazy. When we coincide with any of these selfies, we automatically give an intuitive score regarding the quality and beauty of the selfie. However, it is not really possible to describe what makes a beautiful selfie. There are some obvious attributes but they are not fully prescribed. With … Continue reading Selfai: A Method for Understanding Beauty in Selfies
Paper: https://arxiv.org/pdf/1611.03530v1.pdf This paper states the following phrase. Traditional machine learning frameworks (VC dimensions, Rademacher complexity etc.) trying to explain how learning occurs are not very explanatory for the success of deep learning models and we need more understanding looking from different perspectives. They rely on following empirical observations; Deep networks are able to learn … Continue reading Paper review - Understanding Deep Learning Requires Rethinking Generalization
A crucial problem in a real DL system design is to capture test data distribution with the trained model which only sees the training data distribution. Therefore, it is always important to find a good data splitting scheme which at least gives the right measures to such divergence. It is always a waste to spend … Continue reading Important Nuances to Train Deep Learning Models.
Please ping me if you know something more. Multi-view Face Detection Using Deep Convolutional Neural Network Train face classifier with face (> 0.5 overlap) and background (<0.5 overlap) images. Compute heatmap over test image scaled to different sizes with sliding window Apply NMS . Computation intensive, especially for CPU. http://arxiv.org/abs/1502.02766 From Facial Parts Responses … Continue reading Face Detection by Literature
A successful AI agent should communicate. It is all about language. It should understand and explain itself in words in order to communicate us. All of these spark with the "meaning" of words which the atomic part of human-wise communication. This is one of the fundamental problems of Natural Language Processing (NLP). "meaning" is described … Continue reading Why do we need better word representations ?
<Please let me know if there are more works comparable to these below.> R-CNN minus R http://arxiv.org/pdf/1506.06981.pdf FasterRCNN (Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks) Keywords: RCNN, RoI pooling, object proposals, ImageNet 2015 winner. PASCAL VOC2007: 73.2% PASCAL VOC2012: 70.4% ImageNet Val2 set: 45.4% MAP Model agnostic State of art with … Continue reading Object Detection Literature