7 papers
Accelerated Gradient Descent for Faster Convergence with Minimal Overhead
Manuel Graca, L. Miguel Silveira, Arlindo Oliveira +1
In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in deep learning training tasks. CT-AGD…
Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
Lucas Piper, Arlindo L. Oliveira, Tiago Marques
Convolutional neural networks (CNNs) trained on object recognition achieve high task performance but continue to exhibit vulnerability under a range of visual perturbations and out…
Explicitly Modeling Pre-Cortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
Lucas Piper, Arlindo L. Oliveira, Tiago Marques
While convolutional neural networks (CNNs) excel at clean image classification, they struggle to classify images corrupted with different common corruptions, limiting their real-wo…
Matching the Neuronal Representations of V1 is Necessary to Improve Robustness in CNNs with V1-like Front-ends
Ruxandra Barbulescu, Tiago Marques, Arlindo L. Oliveira
While some convolutional neural networks (CNNs) have achieved great success in object recognition, they struggle to identify objects in images corrupted with different types of com…
Improving Address Matching using Siamese Transformer Networks
André V. Duarte, Arlindo L. Oliveira
Matching addresses is a critical task for companies and post offices involved in the processing and delivery of packages. The ramifications of incorrectly delivering a package to t…
Connecting metrics for shape-texture knowledge in computer vision
Tiago Oliveira, Tiago Marques, Arlindo L. Oliveira
Modern artificial neural networks, including convolutional neural networks and vision transformers, have mastered several computer vision tasks, including object recognition. Howev…
Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning
Manuel Goulão, Arlindo L. Oliveira
The Vision Transformer architecture has shown to be competitive in the computer vision (CV) space where it has dethroned convolution-based networks in several benchmarks. Neverthel…