Solving the Same-Different Task with Convolutional Neural Networks

by   Nicola Messina, et al.

Deep learning demonstrated major abilities in solving many kinds of different real-world problems in computer vision literature. However, they are still strained by simple reasoning tasks that humans consider easy to solve. In this work, we probe current state-of-the-art convolutional neural networks on a difficult set of tasks known as the same-different problems. All the problems require the same prerequisite to be solved correctly: understanding if two random shapes inside the same image are the same or not. With the experiments carried out in this work, we demonstrate that residual connections, and more generally the skip connections, seem to have only a marginal impact on the learning of the proposed problems. In particular, we experiment with DenseNets, and we examine the contribution of residual and recurrent connections in already tested architectures, ResNet-18, and CorNet-S respectively. Our experiments show that older feed-forward networks, AlexNet and VGG, are almost unable to learn the proposed problems, except in some specific scenarios. We show that recently introduced architectures can converge even in the cases where the important parts of their architecture are removed. We finally carry out some zero-shot generalization tests, and we discover that in these scenarios residual and recurrent connections can have a stronger impact on the overall test accuracy. On four difficult problems from the SVRT dataset, we can reach state-of-the-art results with respect to the previous approaches, obtaining super-human performances on three of the four problems.


page 1

page 2

page 3

page 4


Thinking Deeply with Recurrence: Generalizing from Easy to Hard Sequential Reasoning Problems

Deep neural networks are powerful machines for visual pattern recognitio...

Biologically inspired deep residual networks for computer vision applications

Deep neural network has been ensured as a key technology in the field of...

Recurrent Vision Transformer for Solving Visual Reasoning Problems

Although convolutional neural networks (CNNs) showed remarkable results ...

Visualizing Residual Networks

Residual networks are the current state of the art on ImageNet. Similar ...

Tandem Blocks in Deep Convolutional Neural Networks

Due to the success of residual networks (resnets) and related architectu...

Total Recall: Understanding Traffic Signs using Deep Hierarchical Convolutional Neural Networks

Recognizing Traffic Signs using intelligent systems can drastically redu...

Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks

Recent successes in deep learning have started to impact neuroscience. O...

Please sign up or login with your details

Forgot password? Click here to reset