Questions tagged [faster-r-cnn]

For questions related to the faster R-CNN model, which was proposed in "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks" (2015) by Shaoqing Ren et al. and published in NeurIPS. Faster R-CNN is an improved version of fast R-CNN, which, in turn, is an improved version of R-CNN.

Filter by
Sorted by
Tagged with
7 votes
2 answers
746 views

Is there an argument against using the (reviewed) predictions of a model as ground truth to further train exactly this model?

I plan to use my predictions as ground truth to continue training my model. These predictions are of course reviewed during this process. Is there an argument against that (reinforcement of slight ...
user avatar
  • 73
0 votes
0 answers
11 views

What is a good first guess to set hyper parameters for Adam optimiser for Faster RCNN?

Is there a way to make an educated guess on how to set the hyper parameters for Adam optimiser for Faster RCNN depending on the size of the dataset and the loss function? I use the default values for ...
user avatar
0 votes
0 answers
27 views

At which step in faster R-CNN is non-maximum suppression performed?

At which step in faster R-CNN is non-maximum suppression performed? In some book, I have read that it is performed after passing the features through the last fully connected layers, which are located ...
user avatar
  • 1
0 votes
0 answers
66 views

Mask R-CNN: ground-truth vs target vs output masks

The mask branch of Mask R-CNN outputs masks of size $m\times m$ for each class ($k$ in total). How are the outputted masks compared with the target masks, which in general have different sizes from $m\...
user avatar
  • 21
1 vote
0 answers
64 views

Mask R-CNN: how is the inference done?

According to the Mask R-CNN paper and the picture below (taken from the paper), the mask branch is computed in parallel with the bbox classification and regression branches. However in the paper they ...
user avatar
  • 21
1 vote
0 answers
23 views

Why are the learned offsets of anchor boxes in the RCNN object detection models scale invariant?

In the original RCNN paper (https://arxiv.org/pdf/1311.2524.pdf) and continued in later RCNN papers such as faster RCNN (https://arxiv.org/pdf/1506.01497.pdf) the learned offsets of the anchor boxes ...
user avatar
  • 143
0 votes
0 answers
10 views

Why the two identical "IoU comparing procedures" are needed in Faster R-CNN(RPN & RCNN)?

As far as I know, there are two same 'IoU comparing procedures' in RPN and RCNN, but why is the same operation held twice? The paragraph right below is what I've comprehended about the Faster R-CNN. ...
user avatar
  • 1
1 vote
0 answers
24 views

In anchor based object detection, why don't the anchors share the same weights?

After reading about YOLO V3 and Faster R-CNN, I don't understand why the weights for the regression head aren't the same across all boxes of the same size. Given that the backbone of these systems is ...
user avatar
0 votes
1 answer
71 views

Confusion about faster RCNN neither object nor background label

I am trying to construct a faster RCNN from scratch using KERAS. I am generating the tensor which contains whether anchor at each location corresponds to object or background or neither for training ...
user avatar
0 votes
0 answers
24 views

How to design training loop in RPN?

I have a short question. I understand the concept of RPN but one small details keeps me from implementing it. How should I design the training loop given that I have to use only a subset of anchor ...
user avatar
5 votes
1 answer
145 views

How does the region proposal method work in Fast R-CNN?

I read so many articles and the Fast R-CNN paper, but I'm still confused about how the region proposal method works in Fast R-CNN. As you can see in the image below, they say they used a proposal ...
user avatar
  • 51
1 vote
1 answer
576 views

In Faster R-CNN, how can I get the predicted bounding box given the neural network's output?

The RPN loss in Faster RCNN paper is $$ L({p_i}, {t_i}) = \frac{1}{N_{cls}} \sum_{i} L_{cls}(p_i,p_i^*) + \lambda \frac{1}{N_{reg}} \sum_i p_i^* L_{reg}(t_i, t_i^*) $$ For regression problems, we have ...
user avatar