Statistical Analysis Stack Exchange
Statistical Analysis Stack Exchange

Questions tagged [yolo]

"You Only Look Once", a Deep Learning-based object recognition algorithm available in several different software implementations.

"You Only Look Once: Unified, Real-Time Object Detection" by Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi

48 questions
31
votes
5 answers

Yolo Loss function explanation

I am trying to understand the Yolo v2 loss function: \begin{align} &\lambda_{coord} \sum_{i=0}^{S^2}\sum_{j=0}^B \mathbb{1}_{ij}^{obj}[(x_i-\hat{x}_i)^2 + (y_i-\hat{y}_i)^2 ] \\&+ \lambda_{coord} \sum_{i=0}^{S^2}\sum_{j=0}^B…
Kamel BOUYACOUB
  • 341
  • 1
  • 3
  • 3
9
votes
1 answer

Yolo v3 loss function

The original loss function can be seen here and is more or less explained in Yolo Loss function explanation: \begin{align} &\lambda_{coord} \sum_{i=0}^{S^2}\sum_{j=0}^B \mathbb{1}_{ij}^{obj}[(x_i-\hat{x}_i)^2 + (y_i-\hat{y}_i)^2 ] \\&+…
sachinruk
  • 1,113
  • 1
  • 9
  • 21
7
votes
1 answer

On Yolo, and its loss function

I'm having a hard time understanding some on the inner-working of YOLO, especially the loss function depicted in this seminal paper. Bear in mind that I'm nowhere closed to being a specialist in deep learning and computer vision (in fact, I started…
Hermès
  • 173
  • 1
  • 5
5
votes
2 answers

What is sigma function in the YOLO object detector?

I have gone through the YOLO9000 paper, in that they have mentioned that network predicts 5 coordinates of the bounding box, and from that we find the exact centre coordinates and the width and height. I'm confused with those…
bibinwilson
  • 153
  • 3
4
votes
2 answers

How are YOLO anchor boxes generated?

I am recently trying out darkflow, a Tensorflow implementation of Darknet written by Joseph Redmon. Looking at the configuration files, I noticed a section called region as shown below. [region] anchors = 1.08,1.19, 3.42,4.41, 6.63,11.38, …
user3600725
  • 41
  • 1
  • 3
4
votes
1 answer

Yolo loss function for detecting 1 class

I'm trying to work on a Yolo implementation which searches a 19x19 grid to find a specific item. There is only a single class in all of these images I am looking to get bounding boxes for. I'm a little confused about the calculation of the loss…
Michael Bawol
  • 151
  • 4
4
votes
2 answers

Adjusting Grid Size in YOLO?

I was going through the YOLO Object Detection Paper by Joseph Redmon. The authors use a grid size of $S = 7$. If I am not wrong, the network architecture has carefully been curated for this specific grid size (Since the output of the final conv…
Banach Tarski
  • 233
  • 2
  • 8
3
votes
1 answer

What are "Grids" and Detection at different scales" in YOLOV3?

I've recently started working with Yolov3 and the more I go in depth, the more confused I get. In the simplest terms what I think about YOLOV3 (On 416 input, 80 classes, 3 BB) is that: It Extract features from DarkNet-53 and then again use 53…
Deshwal
  • 234
  • 1
  • 8
3
votes
1 answer

Why use multiple anchor boxes with the same positions in a multi-box detector?

What is the benefit of using multiple anchor boxes with the same positions in a single-shot multi-box detector model, like YOLO? In particular, I notice Google's BlazeFace model does this. If the purpose of an anchor box in a multi-box detector is…
algal
  • 133
  • 3
3
votes
1 answer

1 neuron BCE loss VS 2 neurons CE loss

I built a custom version of YOLO that should only detect one type of objects, where the objectness measure (which tells how likely a bounding-box contains an object of any type), is learned using a logistic regression (BCE loss), with a single…
SomethingSomething
  • 145
  • 6
3
votes
0 answers

Yolov3: Single-class vs multiple class

I'm really new to object detection with Yolov3. Let's say I have 10 classes and the amount of data is approximately the same. Do I achieve better average precision when I use 10 Yolo models and train them always with the data of just one class or…
kai Herbst
  • 31
  • 2
3
votes
0 answers

What is the need of multiple Bounding Boxes per grid cell in YOLO v1?

This question is regarding YOLO v1 architecture as in here. I am confused as to why authors have used 2 bounding boxes per grid cell for training. Assuming there can be only one object per grid cell. Would two boxes would be relevant? If yes:…
GeneX
  • 622
  • 7
  • 14
3
votes
1 answer

YOLO loss function width and height component explanation

I am reading this paper on how yolo defines loss function. https://arxiv.org/abs/1506.02640 I did research on other posts, but these posts did not seem to answer my confusion: (How to calculate the class probability of a grid cell in YOLO object…
Earthgod
  • 133
  • 4
2
votes
1 answer

Question YOLOv2 bounding box prior

In the YOLO9000 paper, they define the distance between a box and centroid as $d(box, centroid) = 1 - IOU(box, centroid)$. I think box here is a ground truth bounding box, but what is centroid?
Yandle
  • 743
  • 2
  • 12
2
votes
1 answer

Performance of MaskRCNN/YOLO as a function of object size in pixels

I am trying to find references on how the resolution of an object affects the ability of object detection systems such as MaskRCNN and YOLO to correctly identify the object. For example, if the camera is zoomed further and further out, the number…
Surgical Commander
  • 369
  • 1
  • 3
  • 9
1
2 3 4