Notes on "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks"

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks by Ren et al (2016)

Region proposal based approaches for object detection tends to have the state-of-the-art performances in many benchmark datasets. Faster R-CNN uses convolutional network to propose regions which result in sharing the computation. Therefore, the Faster R-CNN is faster than R-CNN and Fast R-CNN (this is not real time capable!). See the slides below which is taken from a course on convolutional neural network from coursera.


Faster R-CNN uses two convolutional neural networks; one is for the region proposal while other is for detection. As shown below the classifier uses proposals meaning "Region Proposal Network" gives the classifier where to look.

To generate region proposal network, a convolutional network over the feature maps is proposed in which the inputs are n by n spatial window of the input feature map (each slideing window is mapped to a lower dimensional feature which is then fed into box regression layer and class regression layer; image below only shows for one window but it is repeated over all the windows) and the outputs are the proposed regions (anchors - pyramid of k anchors which is more efficient). Note that this approach is translational invariant (multibox methods that use k-means algorithm are not!).

4-step training methods is adapted in order to have regional proposal network and detection network share the features.
  1. RPN is initialized with an ImageNet pretrained model and fine tuned end to end for the regional proposal task.
  2. Fast R-CNN is initialized with an ImageNet pretrained model, and trained separately using the proposals generated by the step 1 RPN (At this point no CNN are shared between RPN and Fast R-CNN).
  3. Detector network is used to initliaze RPN training; fix the shared convlutional layers and only fine tune the layers unique to RPN (Finally CNN are shared).
  4. Fine tune the layers unique to Fast R-CNN while keeping other layers the same.
Rule in any machine learning training is do not use two optimization functions at once! All the details and the source codes are available. This method is evaluated with PASCAL VOC and other publicably available dataset. 


Q&A:

Comments

Post a Comment

Popular posts from this blog

Notes on "Focal Loss for Dense Object Detection" (RetinaNet)

Image
Focal Loss for Dense Object Detection by Lin et al (2017) The central idea of this paper is a proposal for a new loss function to train one-stage detectors which works effectively for class imbalance problems (typically found in one-stage detectors such as SSD). The authors also introduce RetinaNet based on the proposed loss function which outperforms the state-of-the-art detection algorithms including the two-stage detectors. Focal loss function: pt is defined as p if y = 1 and p-1 otherwise. In this way, CE(pt) is the cross entropy where p is the probability score. As shown below, the cross entropy is denoted blue (gamma = 0). By adding the factor (see the focal loss FL(pt)) the loss function computes smaller value for the well classified examples and puts more focus on hard and misclassified eamples. In this way the easy background examples are dealt with, which enables the training of highly accurate desne object detection algorithms. Just like alpha-cross entropy is the comm
Read more

Introduction to Bayesian methods

Image
Introduction to Bayesian methods: 1. Bayesian way of thinking: A man is running. Why? Some of the possible explanations are (1) this man is in hurry, (2) this man is running, (3) this man just spotted a dragon, and (4) this man always runs. There are three principles in Bayesian way of thinking which we can use to conclude which of these explanations are the most reasonable. These principles are: 1. Use the prior knowledge on the problem - there is no dragon. 2. Choose the answer that explains the data the most - the man is not wearing the runner. 3. Avoid making extra assumptions - crude to think that any man always run. The answer number "1. this man is in hurry" should be chosen following this principles. 2. Review of probability: Checklists are: 1. What is the probability? 2. What are random variables? 3. What is the probability mass function (PMF)? 4. What is the probability density function (PDF)? 5. What does it mean for the random variables X and Y
Read more

Conjugate Priors

Conjugate Priors. 1. Analytical inference: See the Bayes formulae. The problem is that the evidence is difficult to estimate for the analytical inference. One way to get away is the maximum posterior (MAP) and is very easy to compute, but it comes with many problems. 1. Lack of the in-variance to re-parameterization. 2. The MAP cannot be used as the prior. 3. The MAP is an untypical point (the mode). 4. The credible regions may not be computed. 2. Conjugate distributions. Another approach to avoid computing the evidence is called the conjugate distributions. As the likelihood and the evidence is fixed by our model, we can only vary the prior so that it is easier to compute the posterior. I f the posterior distribution p(θ|x) are in the same family as the prior distribution p(θ), the prior and posterior are then called conjugate distributions, and the prior is called a conjugate prior for the likelihood. For example, the Gaussian family is conjugate to itself (or self-
Read more