Explore our questions

0 votes
0 answers
22 views

Realtime cuboid vs cylinder classification of a 2D mask / object from a 3D scene?

0 votes
0 answers
6 views

1D CNN with Single vs. Two Channels for Number Image Recognition

0 votes
0 answers
5 views

Can you iteratively freeze and unfreeze parts of a neural network for efficient training?

4 votes
1 answer
490 views

How should I define the loss function for a multi-object detection problem?

0 votes
1 answer
154 views

Fine-Tune Llama on main and auxiliary task

0 votes
0 answers
13 views

Why the architeture of Resnet18 is suitable to images classification?

0 votes
0 answers
16 views

High-resolution 3D human digitization from a single image or multiple images

0 votes
1 answer
135 views

Keypoint generation in 3D point clouds with Deep Learning

0 votes
2 answers
211 views

How do multimodal models establish connections between different modes?

0 votes
1 answer
123 views

How vision models based on CNNs learn the relative positions of each pixel in the image?

1 vote
0 answers
19 views

why we use learnable positional encoding instead of Sinusoidal positional encoding

0 votes
0 answers
15 views

Train a network to find the most sharp image from a group of images

2 votes
0 answers
27 views

Current state of MoE models

0 votes
1 answer
165 views

Semantic segmentation failing in small instance detection

Browse more Questions