3

TL;DR This is possible. You need a correctly labeled dataset. Your dataset has two labels: $y\in \{\text{background},\text{object in frame}\}$ or simply $y\in \{0,1\}$ This labelling avoids needing to know what object is in frame only that there is an object in frame. Examples With Similar Objectives Here as a paper (link) that was seeking to classify ...


3

Facial classification and tracking is easier compared to tracking any other motion. This is due to the fact that the face have a large number of easily identifiable features. Facial tracking is an additional layer on top of facial detection. Facial detection works by finding characteristics such as the cheekbones, chin, nose, eyes etc. These features are ...


3

Aesthetics of images has a strong subjective element and possibility of multiple dimensions depending on purpose of the media. That means: It is hard to define what we mean by scoring aesthetics. Given any well-constrained definition, it is then time-consuming to collect relevant data. However, there is some interest in the machine-learning community, as ...


3

Yes, it has been demonstrated that the main factor for CNNs to work is its architecture, which exploits locality during the feature extraction. A CNN with random weights will do a random partition of the feature space, but still with that spatial prior that works so well, so those random features are OK for classification (and sometimes even better than ...


3

tl;dr What does that mean in the context of this paper? With "coarse segmentation" the author means a segmentation that doesn't have much detail. "Fine segmentation", on the other hand, refers to a segmentation with a high level of detail. But also more importantly [what does that mean in the context of] general computer vision? The most common use ...


3

I think you are slightly confusing 2 problems. 1 being classification of meta visual elements and the other being the visual system itself. Our visual system, when it comes to processing information, has had billions of years of iteration(training), so that at birth(and before), we are already tuned for the processing of visual stimuli, as well as have the ...


3

I've seen this too many times - it's not a problem with your network, it's a problem with matplotlib and how it displays the image. You are probably trying to display a float with range $<0, 255>$. When matplotlib sees float type as input, it assumes a range of $<0, 1>$, and thresholds everything outside of that range, and the results you can see....


3

One of the methods which is quite fast and easy to implement. You can do Principal Component Analysis (PCA) based face recognition. You can go through this paper for the theory behind it. For an example implementation you can see this blog post. The process, roughly, is as following: If you have a grayscale image of size $(20,20)$, then this image can be ...


2

So this paper is by google, but is very similar where they use 2D positional embeddings and perform MHA on the flattened image. Are you talking about Attention Augmented Convolutional Networks


2

FastAI is the most “out of the box” API for this type of task. For video examples (and a little theory) check out the MOOC section of their site. Practical Deep Learning and Cutting Edge Deep Learning are the two sections most relevant to you. But if you want a working implementation check out this GitHub repo that implements SSD for your purposes. I ...


2

The Wikipedia article related to computer vision gives, in my opinion, a good description of the field and its relation to image processing. Below, I will only cite the most relevant parts of the article. Computer vision is an interdisciplinary scientific field that deals with how computers can be made to gain high-level understanding from digital images ...


2

Why is ImageNet so popular for transfer learning? Models pre-trained on the ImageNet datasets have been the de-facto choice for many years now. Many popular reasons as to why people think that ImageNet is so effective for transfer learning are the following: ImageNet is a truly large-scale dataset that contains over 1 million images, each of which has a ...


2

The abbreviations sim2sim, sim2real and real2real refer to techniques that can be used to transfer knowledge from one environment (e.g. in simulation) to another one (e.g. in the real world). sim2sim stands for simulation-to-simulation, sim2real stands for simulation-to-real, and real2real stands for real-to-real. In sim2sim, knowledge acquired during ...


2

Overview As it has already been observed, your main problem, beside the training related issues like fixing the learning rate, is you have basically no chance to learn such a big model woth such a small dataset ... from scratch So focusing on the real problem, here are some techniques you could use dataset augmentation transfer learning from a ...


2

Try lowering the learning rate. Such a loss curve can be indicative of a high learning rate. Due to a high learning rate the algorithm can take large steps in the direction of the gradient and miss the local minima. Then it will try to come back to the minima in the next step and overshoot it again. You may also try switching to a momentum-based GD ...


2

Father Ted explains why this is a hard problem. Seriously -- if you have stereo images it should be possible, since that's what we use for depth perception. If you know how far away points x1 and x2 are, then you can measure distance using trigonometry. No neural networks needed, I guess. https://en.wikipedia.org/wiki/Triangulation_(computer_vision)


2

If the measurements you want from the object aren't too complicated (ie. length of a clearly defined feature), and if you are able to acquire a training dataset of images of the objects similar to what your model will see in your use case (same scale/distance), their bounding boxes and their measurements, a model you could try to implement is a Multi-Task ...


2

Bot development is more about 'hacking' than AI in a way that in the very first place you need to read and (over) write game data which you are not supposed to (and thereby potentially violating the Terms and Conditions - so be aware of that). The AI part is fairly simple for most hack/bot applications that I can think of. Read data To read game data you ...


2

There are hundred of papers on this task some older than I am! Normally this is done by trying to form a box shape around the image than estimate the volume. This task is typically done with multiple images so the two can generate a more clear picture of the size of the object than one image alone. An object could be 'infinitely' large but its mass could be ...


2

You should use both classes together. Let's say you use the method you proposed. Then they will be contradicting each other as one teaches the network to recognize people, not objects and the other teaches the network to recognizes objects not person. There is no need for seperation of the two classes, unless you are making two seperate classifier. Hope I ...


2

After a quick scan, it would seem that, in the history of object detection, machine learning has always been at the forefront. Before then, it would just be a heuristic approach. For a quick answer, here: https://towardsdatascience.com/real-time-object-detection-without-machine-learning-5139b399ee7d That goes over object detection without using machine ...


2

The paper you are citing is the paper that introduced the cascaded convolution neural network. In fact, in this paper, the authors say To realize 3DDFA, we propose to combine two achievements in recent years, namely, Cascaded Regression and the Convolutional Neural Network (CNN). This combination requires the introduction of a new input feature which ...


2

Since you have already tried U-Net. You may look into Siamese Networks (with CNNs for images), they are very well known for computing similarity via deep learning. This is a central idea and can be performed with both text and images. As a tip, you may be able to leverage a lot of architecture from U-Net to Siamese. Hope it helps, Some useful links to ...


1

If you have a $h_i \times w_i \times d_i$ input, where $h_i, w_i$ and $d_i$ respectively refer to the height, width and depth of the input, then we usually apply $m$ $h_k \times w_k \times d_i$ kernels (or filters) to this input (with the appropriate stride and padding), where $m$ is usually a hyper-parameter. So, after the application of $m$ kernels, you ...


1

Step one, engage with the seniors. Since, self-driving is a complex task the seniors are (with high probability) using a pipelined system with multiple modules. Ask them for a ceiling analysis. If they do not know what that is (you've already wowed them). Assuming that they know what ceiling analysis is, they can provide you with one for one of their ...


1

One of the key terms in the literature that you are looking for is video captioning. You can have a look at some of the relevant papers with code on this subject. In short, it is an active area of research and a difficult problem, one reason is because videos are still difficult to learn about (because of larger amount of data + larger model, etc...) and ...


1

I've worked on the BRATS dataset and I can verify that this is pretty much standard process. Besides throwing the totally blank images, I also throw away the images in the beginning and ending of the sequence that show the tip of the scull and the base of the neck. Generally when dealing with MRIs, I do this with a script (think of is as a preprocessing ...


1

The model (that I know of) which most resembles your description is the auto-encoder, which is trained to learn a compact representation (a vector) of the input, which can later be used to reconstruct the original input. In a certain way, this compact representation (implicitly) encodes the most important features of the input. In particular, you may be ...


1

Nicola Bernini's answer is quite comprehensive. Here are my insights. First of all, think whether you really need neural networks to solve your problem. Think whether traditional computer vision operations like edge detection/ region-based methods help you to solve your problem (OpenCV can help you here). Think about your data again. In case you decide to ...


1

Looking at it from the perspective of input to output in that fashion is probably not the best. So lets start with our goal and how these ND convolutions accomplish that (Note these are in my own words, and may not be best stated). Assumption: There exists highly correlative local associations Goal: Have a linear model that takes advantage of these ...


Only top voted, non community-wiki answers of a minimum length are eligible