61 votes
Accepted

How is it possible that deep neural networks are so easily fooled?

First up, those images (even the first few) aren't complete trash despite being junk to humans; they're actually finely tuned with various advanced techniques, including another neural network. The ...
Ben N's user avatar
  • 2,599
28 votes

How is it possible that deep neural networks are so easily fooled?

The images that you provided may be unrecognizable for us. They are actually the images that we recognize but evolved using the Sferes evolutionary framework. While these images are almost impossible ...
Vishnu JK's user avatar
  • 1,072
28 votes
Accepted

What is a fully convolution network?

Fully convolution networks A fully convolution network (FCN) is a neural network that only performs convolution (and subsampling or upsampling) operations. Equivalently, an FCN is a CNN without fully ...
nbro's user avatar
  • 40.5k
17 votes

How is it possible that deep neural networks are so easily fooled?

All answers here are great, but, for some reason, nothing has been said so far on why this effect should not surprise you. I'll fill the blank. Let me start with one requirement that is absolutely ...
Maxim's user avatar
  • 1,957
11 votes

How is it possible that deep neural networks are so easily fooled?

An important question that does not yet have a satisfactory answer in neural network research is how DNNs come up with the predictions they offer. DNNs effectively work (though not exactly) by ...
Harsh's user avatar
  • 1,315
10 votes
Accepted

In Computer Vision, what is the difference between a transformer and attention?

The original transformer is a feedforward neural network (FFNN)-based architecture that makes use of an attention mechanism. So, this is the difference: an attention mechanism (in particular, a self-...
nbro's user avatar
  • 40.5k
9 votes
Accepted

When using neural networks to detect features in an image, how can locate that specific feature in the original image?

This problem is called object detection. If you have a trainings set of images with boxed objects you can just train a neural network to directly predict the box. I.e. the output has the same ...
BlindKungFuMaster's user avatar
8 votes
Accepted

Why does nobody use decision trees for visual question answering?

For vision tasks, neural network models almost always include a number of layers that pool and convolute. The convolutions, in particular, are very useful - they can make the model generalize better ...
Greenstick's user avatar
8 votes

What could an oscillating training loss curve represent?

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 ...
Nicola Bernini's user avatar
8 votes
Accepted

How do you find the homography matrix given 4 points in both images?

To understand homographies and how to find them, you will need a good dose of projective geometry. I will briefly describe some preliminary concepts that you need to know before trying to find the ...
nbro's user avatar
  • 40.5k
8 votes
Accepted

What are the main algorithms used in computer vision?

There are many computer vision (CV) algorithms and models that are used for different purposes. So, of course, I cannot list all of them, but I can enumerate some of them based on my experience and ...
nbro's user avatar
  • 40.5k
8 votes
Accepted

Is it okay to use publicly available Instagram videos to train an AI?

Under US copyright law, this is probably fair use ...but beware of memorization. You may run into more trouble if the AI outputs things very similar to the original work. Also, consult a lawyer to ...
Ryan M's user avatar
  • 196
8 votes
Accepted

What is an appropriate size for a latent space of (variational) autoencoders and how it varies with the features of the images?

You are asking about several things here and while related, solving one, will not necessarily "solve" your problem. Let's look at them separately: Optimal dimension of the latent space. ...
Евген's user avatar
7 votes
Accepted

Why would neural network dream scenes mirror the hallucinations people experience when they're tripping?

The similarity of artificial neural networks and the human visual cortex goes very deep, and in many ways the human visual cortex was the inspiration for the techniques we use for the design and ...
Matthew Gray's user avatar
  • 4,262
7 votes

Why is no activation function used at the final layer of super-resolution models?

I am not into the field of super-resolution, but I think this question applies to general neural network construction. Usually, you try to solve a classification problem or a regression problem with ...
Marcel_marcel1991's user avatar
7 votes

What could an oscillating training loss curve represent?

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 ...
Sabyasachi Ghosh's user avatar
7 votes
Accepted

How to calculate the distance between the camera and an object using Computer Vision?

In general, calculation of distance between camera and object is impossible if you don't have further scene dependent information. To my knowledge you have 3 options: Stereo Vision If you have 2 ...
Mr Vinagi's user avatar
  • 186
7 votes
Accepted

Why different noise in GAN generate different images?

Let's take this apart. GANs stand for Generative Adversarial Networks. Your question is how GANs are generative (the G part of the name). For this we need to understand what they try to achieve. In ...
sfotiadis's user avatar
  • 301
6 votes
Accepted

Do deep learning algorithms represent ensemble-based methods?

You should think of them as different approaches. A deep neural net is a single independent model, whereas ensemble models are ensembles of many independent models. The primary connection between the ...
Matthew Gray's user avatar
  • 4,262
6 votes

What do the words "coarse" and "fine" mean in the context of computer vision?

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 ...
Djib2011's user avatar
  • 3,183
6 votes
Accepted

Is it true that untrained CNNs can be used as feature extractors?

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 ...
David's user avatar
  • 511
6 votes
Accepted

How can I estimate how many photos I need to train ResNet-50 for image classification?

What you want to calculate/estimate is known as the sample complexity in computational learning theory. If you knew the VC dimension of the neural network, you may be able to estimate the sample ...
nbro's user avatar
  • 40.5k
6 votes

Why diffusion model always use U-Net?

I don't have a definitive answer but I'd state my intuitions anyways: Diffusion models are highly related to the idea of stacked denoising autoencoders [Kumar et al. (2014)]. Additionally, U-Net-like ...
Chillston's user avatar
  • 1,704
5 votes

How is it possible that deep neural networks are so easily fooled?

How is it possible that deep neural networks are so easily fooled? Deep neural networks are easily fooled by giving high confidence predictions for unrecognizable images. How is this possible? Can you ...
Rob's user avatar
  • 632
5 votes
Accepted

What are bag-of-features in computer vision?

Introduction Bag-of-features (BoF) (also known as bag-of-visual-words) is a method to represent the features of images (i.e. a feature extraction/generation/representation algorithm). BoF is inspired ...
nbro's user avatar
  • 40.5k
5 votes
Accepted

Formal definition of the Object Detection problem

This is just an idea Given a set of pixels, the task is to decide: Which pixel is the center of an object? What is the size of the bounding boxes with the center is the pixel in part 1? Formula, ...
CuCaRot's user avatar
  • 912
5 votes
Accepted

Do Vision Transformers handle arbitrary sequence lengths the same way as normal Transformers?

Yes, they can handle sequences with arbitrary length sequence, but with some remarks. In the paper Training data-efficient image transformers & distillation through attention authors train models ...
spiridon_the_sun_rotator's user avatar
4 votes
Accepted

Applications of CNN for detecting crime from video surveillance cameras

After a bit of research I found something kind of close: Artificially intelligent security cameras are spotting crimes before they happen New surveillance cameras will use computer eyes to find 'pre ...
Avik Mohan's user avatar
4 votes
Accepted

How does Pinterest decipher what's on unmarked pictures and categorize them?

One of the Pinterest's white paper about Human Curation and Convnets powering item-to-item recommendationsarxiv describes implementation of convolutional neural network (CNN) based visual features (...
kenorb's user avatar
  • 10.5k
4 votes

How is it possible that deep neural networks are so easily fooled?

Can't comment(due to that required 50 rep), but I wanted to make a response to Vishnu JK and the OP. I think you guys are skipping the fact that the neural network only really is saying truly from a ...
Metric's user avatar
  • 51

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