Skip to main content

Questions tagged [computer-vision]

For questions related to computer vision, which is an interdisciplinary scientific field (which can e.g. use image processing techniques) that deals with how computers can be made to gain high-level understanding from digital images or videos. For example, image recognition (that is, the identification of the type of objects in an image) is a computer vision problem.

Filter by
Sorted by
Tagged with
0 votes
0 answers
40 views

What computer vision techniques can help me select the best image for object detection inference?

I have a lot of duplicate images. I need to make a selection to reduce the amount of images the Mask RCNN model will perform inference on. In every collection of duplicates, the images slightly differ....
Nick De Wispelaere's user avatar
1 vote
0 answers
619 views

Latent Diffusion Model Can't Learn the Latent Space of a VAE for the MNIST-Fashion Dataset

I'm currently playing around with LDMs on the MNIST-Fashion dataset. I thought the VQVAEs used in the original paper were a bit overkill for what I'm doing (and I don't fully understand how they ...
sb3's user avatar
  • 147
1 vote
2 answers
267 views

How do you name your deep learning training outputs?

After some time starting the deep learning project, training output files (model weights,training configuration files) will be piled up. Naming all outputs and training files can become complicated if ...
Ugurcan's user avatar
  • 121
1 vote
1 answer
133 views

How to ensure continuity of AI model logic?

I am aware that this question might be vague but I must try anyways. I am looking for a method or an algorithm or even just some keywords (to conduct further research) of how to deal with phenomenon ...
GKozinski's user avatar
  • 1,270
1 vote
0 answers
265 views

How can I solve the blurring problem in GAN generated images?

In my project I work in dresses dataset. I can solve the problem of black pixels but blurring still existed. I tried many computer vision filters like median filter, Biliteral filter, Sharpen methods ...
Abeer Elmorshdy's user avatar
1 vote
0 answers
45 views

Why is my validation accuracy fluctuating between two inverse values?

I am currently going through the FastAI course and to practise, I wanted to code a neural network that classifies the FashionMNIST dataset from scratch. Lately, I've been running into an issue where I ...
DerOeko's user avatar
  • 13
4 votes
2 answers
2k views

Why does CLIP use a decoder-only transformer for encoding text?

In CLIP [1], the authors train a model to learn multi-modal (text, vision) embeddings by maximizing the cosine similarity between text and image embeddings produced by text and image encoders. For the ...
thesofakillers's user avatar
1 vote
1 answer
191 views

Are there any advantages of encoding an image as a graph to use in Graph Convolutional Networks?

I have seen this encoding of an image as a graph: The set of the nodes $V$ is the set of pixels. If the image is of size $10\times10$, then we have $10\cdot10=100$ pixels. Each node has a length 3 ...
puradrogasincortar's user avatar
3 votes
0 answers
57 views

Why do adversarial attacks work on CNNs if they classify images as humans do?

A common illustration on how CNN works is as follows: https://www.researchgate.net/figure/Learned-features-from-a-Convolutional-Neural-Network_fig1_319253577. It seems to suggest that CNN in ...
Sam's user avatar
  • 195
3 votes
2 answers
630 views

Does the position of the tokens in Vision Transformer matter?

I am reading through the Vision Transformer paper and other related papers, such as DeiT and Visual Prompt Tuning (VPT). I wonder if the position of the tokens that flow through the Transformer encode ...
Minh-Long Luu's user avatar
0 votes
2 answers
141 views

How can I use CNN to make a cumulative count of the number of occurrences of each of the different objects in all the images in the test set?

Let's say there are three images in the test set, the first with three triangles, the second with two triangles and two circles, the third with four circles and two squares, and the final tally is a ...
El J 1e2's user avatar
-1 votes
1 answer
63 views

What is the Need for AI Developers since we have AI APIs Now?

I am new to AI and passionate about it. I have a fair knowledge of deep learning and I am into computer vision. I am eyeing NLP as well. I just want to know the need for an AI developer in computer ...
Mr Prof's user avatar
  • 101
0 votes
1 answer
72 views

Best way to generate a human face over a face generated by FaceFormer framework?

FaceFormer framework generates a talking face from audio, focusing on the lip and face movement when a person talks. Now from that what would be the best way to generate a human face on top of that? I ...
Sadaf Shafi's user avatar
2 votes
0 answers
46 views

Can Inception-ResNet be inverted layer-by-layer?

It has already been shown that by using a normalization layer during training, it is possible to invert a residual network layer-by-layer. I wonder how similar Inception-ResNet is and whether a ...
Richie Bendall's user avatar
1 vote
1 answer
498 views

Are there any books that teach text-to-image generation?

I read some of the research papers about text-to-image generation using Imagen, DALL-E 2, etc. but they are heavily scientific and I don't understand a lot of their concepts, so I was wondering are ...
user avatar
0 votes
1 answer
93 views

How do L2 norm and Jacobian act as a regularisation term to encourage smoothness in a deformation field?

How do L2 norm and The Jacobian act as a regularisation term to encourage smoothness in a deformation field? from the VoxelMorph original paper (here) they used Jacobian as a means to smoothen the ...
a__ys's user avatar
  • 3
1 vote
1 answer
121 views

How is the variance for a diffusion kernel derived for a diffusion model?

So I'm watching this video tutorial from CVPR this year on diffusion models, and I am confused by the variance term in the distribution on the left on the video. I understand that in the forward ...
Cynthia Kim's user avatar
1 vote
1 answer
82 views

Group image classification for whether containing unrelated images

I'm kind of new to computer vision, and wondering whether this is any existing researches / solutions to following scenarios. Suppose I have a dataset, each data point contains a few images (< 20 ...
misakayu's user avatar
0 votes
1 answer
118 views

Are there metrics for image complexity for informing neural network design?

BACKGROUND: I am trying to think of rational approaches to designing deep learning models for image classification. One thought is to quantify the complexity of image datasets and use that to inform ...
Snehal Patel's user avatar
0 votes
1 answer
71 views

Segmentation of x-ray images to detect Covid-19

I’m currently working on covid detection project using x-rays. I applied K -means clustering algorithm (https://www.kaggle.com/code/naim99/image-classification-clustering-step-by-step?scriptVersionId=...
S i's user avatar
  • 1
0 votes
0 answers
3k views

How does Tesla's autopilot generate 3d reconstruction of road?

Tesla uses stereo vision and in many applications it works OK but ground reconstruction is uniquely difficult since there aren't features to match. I'm wondering how 3d reconstruction works here? Does ...
FourierFlux's user avatar
0 votes
1 answer
38 views

How are OCR training datasets constructed?

For the sake of concreteness: let's suppose that the word "OCR" refers to any OCR system build on an R-CNN architecture. Similarly, in aims of simplicity, let's declare that we are ...
Ramiro Hum-Sah's user avatar
1 vote
1 answer
150 views

Detecting individual multiple documents in a pdf [closed]

I need to solve a problem whereas a scan of multiple documents (contracts, invoices, bank extracts) is stored into a PDF and I need to identify how many individual documents are contained in the PDF ...
Jorge Rodrigues dos Santos's user avatar
0 votes
2 answers
2k views

What is the difference between face identification, face verification, and face recognition?

I am confused. On some websites, face identification is just face detection, while face verification is finding the person's identification. They are both considered components of face recognition. ...
Faizan Riasat's user avatar
1 vote
1 answer
72 views

Deep Clustering Approach for Unsupervised Video Anomaly Detection

I'm working on Unsupervised Video Anomaly Detection, and I've tried implementing the Generative Cooperative Learning method, with the help of this paper. The method uses a fixed backbone (ResNext-101) ...
satan 29's user avatar
  • 141
0 votes
0 answers
51 views

openVINO human pose

Can someone give me a tip on what to research for predicting human pose with computer vision with the open VINO toolkit? Not a lot of wisdom here so any tips appreciated even at a high level on what I ...
bbartling's user avatar
  • 101
0 votes
1 answer
56 views

Is there a best practice for creating multiple convolutional layers from small image inputs?

With all the work being done on larger and larger images, I'd like to ask if a best practice(s) has arisen for allowing multiple convolutional layers on small image inputs? For instance, in my case I ...
Josh's user avatar
  • 99
2 votes
2 answers
6k views

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

I am training an autoencoder and a variational autoencoder using satellite and streetview images. I have tested my program on standard datasets such as MNIST and CelebA. It seems that the latent space ...
Qingyi Wang's user avatar
2 votes
2 answers
322 views

Is Computer Vision always related to Machine Learning?

So I have AI project about motion detection with image subtraction. Regardless what are the object used, if there are change between two frames according threshold ...
Muhammad Ikhwan Perwira's user avatar
0 votes
0 answers
500 views

How to increase accuracy for CNN?

I have built one CNN model and applied it to chest-xray Covid 19 pneumonia dataset. I am getting the classification report as follows: I am surprised to see that it is giving an excellent result on ...
XYZ's user avatar
  • 121
1 vote
1 answer
95 views

Survey on non-machine learning object detection algorithms

I am working on a project in which I will be performing object detection on deformed objects. Unfortunately, there isn't enough data sets to train them on some neural network. I am looking for ...
UserX's user avatar
  • 13
4 votes
3 answers
9k views

Why diffusion model always use U-Net?

I want to know why diffusion models always use U-Net. In my opinion, they use U-Net because you can see features of different resolutions and skip connection is good to add detail of images. But I am ...
Penguin.jpg's user avatar
0 votes
0 answers
45 views

How to classify images which are slightly different from each other?

(I hope I'm in the right place to ask such a question.) A robot has a fixed camera which takes images before extending its sticks to grab a box from two sides and pull it back. But if the box is not ...
bit_scientist's user avatar
3 votes
2 answers
425 views

Examples where AI fails in revealing ways

For a short presentation about AI, I am looking for examples where AI failed and thereby shows the limits of itself. I remember there was one example,where an image classifier was given an image of ...
Nathan's user avatar
  • 143
0 votes
2 answers
27 views

How to filter out class for which the model has not been trained in ml web app?

I have developed an python based ml web app. It gives details of the book from a image of book cover. Problem: When I upload the book cover image then it works but when i click image of any random ...
Durgendra's user avatar
1 vote
0 answers
39 views

Pseudo Label Generation for Generative Cooperative Learning

I am trying to implement this paper for unsupervised video anomaly detection. The gist of the paper seems to be: Create a dataset for an unsupervised setting, by mixing up the train and anomalous ...
satan 29's user avatar
  • 141
0 votes
1 answer
46 views

How to use strong labels in image classification?

I have a dataset where I have the labels cancer & non-cancer, and I also have localized pixel-level annotation masks of important regions/features in the images. In a binary classification task, ...
Tirtha's user avatar
  • 11
1 vote
0 answers
33 views

How does a CNN work in detecting absence of features?

I'm trying to understand how a CNN operates internally. Let's say I'm doing binary classification with 1 output neuron and a sigmoid to classify dog vs no dog. No dog meaning the image does not ...
Tirtha's user avatar
  • 11
-1 votes
2 answers
259 views

What is the relationship between data science, artificial intelligence,machine learning and computer vision?

I am beginner to this field and i am trying to find big picture and i have tried to explore youtube and google images in this regard. According to my understanding ,machine learning is subset of ...
DSP_CS's user avatar
  • 171
0 votes
0 answers
83 views

At what size does a picture become unusable for facial recognition?

Lets say i have a portrait photo of which the face it contains covers about 90% of the entire photo. I want to be able to detect the face in this photo using facial recognition but i also want to ...
Maurice's user avatar
  • 133
2 votes
0 answers
32 views

Brain Segmentation To 3D Model

My goal is to take a dataset of Brain Tumor segmentations, use computer vision to locate and highlight the tumor in each slice, then combine each slice (almost like stacking) to make a 3D model. In ...
Abrahim Mahmud's user avatar
0 votes
1 answer
27 views

Question regarding matlab computer vision application and color recongnition [closed]

I am thinking of choosing a computer vision project for my school project(detect crack on surface) and the duration I have is roughly 4 months. With no prior knowledge in neural network, is matlab ...
chuackt's user avatar
  • 107
0 votes
1 answer
118 views

Reconstructing 3D models from 2D images using autoencoders

I went through a research paper ("Voxel-Based 3D Object Reconstruction from Single 2D Image Using Variational Autoencoders") and tried to implement the approach following this diagram: ![...
arizona_3's user avatar
1 vote
0 answers
44 views

Help with model architecture for a racing game

I’m working on a model for a racing game using pytorch. The model gets frame from the game as input and produces a controller state as output. The dataset consists of frames from the game and ...
dht2003's user avatar
  • 11
0 votes
1 answer
199 views

Metrics using batches v/s metrics using full dataset

I am using training an image classification model using the pre-trained mobile network. During training, I am seeing very high values (more than 70%) for Accuracy, Precision, Recall, and F1-score on ...
learner's user avatar
  • 151
0 votes
1 answer
44 views

Image classifier model which predicts objects and it's relevant areas with a combination of words

I have experience with image classification models such as CNN and Vision Transformers but this time I want to try a new thing (For me). First please check the below image to understand what I want ...
albert's user avatar
  • 3
-1 votes
1 answer
36 views

Is regularization in machine learning and deep learning same [closed]

As there are L1 , L2 , etc out and other technique are those all same for machine learning and deep learning while using Ml algorithm and DL algorithm
Shreneek Upadhye's user avatar
0 votes
0 answers
90 views

What is single object localization?

Object detection is said to be combination of object localization and image classification. However, when reviewing localization, I often come across the term "single-object" localization, ...
akastack's user avatar
2 votes
0 answers
104 views

When are traditional image processing methods preferable to machine learning and why?

By traditional image processing I understand, e. g. using filters to improve the image, extracting edges and then classifying objects using template matching. My current decision criteria are: large ...
el123's user avatar
  • 21
1 vote
1 answer
102 views

Does rule-based image processing count as AI?

I'm quite new to the field of AI and I currently find it hard to precisely inclose the broad field of AI. Especially the aspect of image processing isn't quite clear to me. So far I've done rule-based ...
konrad1795's user avatar

1 2
3
4 5
11