Search Results for author:
Found 13 papers, 9 papers with code
LOSSGRAD: automatic learning rate in gradient descent
In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training.
KrakN: Transfer Learning framework for thin crack detection in infrastructure maintenance
Monitoring the technical condition of infrastructure is a crucial element to its maintenance.
Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications.
Hard hat wearing detection based on head keypoint localization
In recent years, a lot of attention is paid to deep learning methods in the context of vision-based construction site safety systems, especially regarding personal protective equipment.
Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference
The computational cost of transformer models makes them inefficient in low-latency or low-power applications.
Finding the Optimal Network Depth in Classification Tasks
We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads.
Continual Learning with Guarantees via Weight Interval Constraints
We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting.
Computer Vision based inspection on post-earthquake with UAV synthetic dataset
The area affected by the earthquake is vast and often difficult to entirely cover, and the earthquake itself is a sudden event that causes multiple defects simultaneously, that cannot be effectively traced using traditional, manual methods.
Adversarial Examples Detection and Analysis with Layer-wise Autoencoders
We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network.
SLOVA: Uncertainty Estimation Using Single Label One-Vs-All Classifier
The proposed classifier is confident only if a single class has a high probability and other probabilities are negligible.
Face Identity-Aware Disentanglement in StyleGAN
Conditional GANs are frequently used for manipulating the attributes of face images, such as expression, hairstyle, pose, or age.
SADMoE: Exploiting Activation Sparsity with Dynamic-k Gating
Transformer models, despite their impressive performance, often face practical limitations due to their high computational requirements.
