Search Results for author:
Found 20 papers, 6 papers with code
Beyond the Known: Enhancing Open Set Domain Adaptation with Unknown Exploration
In this work, we introduce a new approach to improve OSDA techniques by extracting a set of high-confidence unknown instances and using it as a hard constraint to tighten the classification boundaries.
An Edge Computing-Based Solution for Real-Time Leaf Disease Classification using Thermal Imaging
Deep learning (DL) technologies can transform agriculture by improving crop health monitoring and management, thus improving food safety.
Exploiting the Segment Anything Model (SAM) for Lung Segmentation in Chest X-ray Images
Segment Anything Model (SAM), a new AI model from Meta AI released in April 2023, is an ambitious tool designed to identify and separate individual objects within a given image through semantic interpretation.
Residual-based Adaptive Huber Loss (RAHL) -- Design of an improved Huber loss for CQI prediction in 5G networks
Here, we argue that the Huber loss function is more suitable for CQI prediction, since it combines the benefits of both MSE and MAE.
Transferable-guided Attention Is All You Need for Video Domain Adaptation
DTAB compels ViT to focus on the spatio-temporal transferability relationship among video frames by changing the self-attention mechanism to a transferability attention mechanism.
Budget-Aware Pruning: Handling Multiple Domains with Less Parameters
We achieve this by encouraging all domains to use a similar subset of filters from the baseline model, up to the amount defined by the user's budget.
CNNs for JPEGs: A Study in Computational Cost
In this paper, we propose a further study of the computational cost of deep models designed for the frequency domain, evaluating the cost of decoding and passing the images through the network.
Tightening Classification Boundaries in Open Set Domain Adaptation through Unknown Exploitation
Convolutional Neural Networks (CNNs) have brought revolutionary advances to many research areas due to their capacity of learning from raw data.
Productive Crop Field Detection: A New Dataset and Deep Learning Benchmark Results
In precision agriculture, detecting productive crop fields is an essential practice that allows the farmer to evaluate operating performance separately and compare different seed varieties, pesticides, and fertilizers.
From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks
In the last decade, exponential data growth supplied machine learning-based algorithms' capacity and enabled their usage in daily-life activities.
Budget-Aware Pruning for Multi-Domain Learning
Nevertheless, the models are usually larger than the baseline for a single domain.
Mixup-based Deep Metric Learning Approaches for Incomplete Supervision
Deep learning architectures have achieved promising results in different areas (e. g., medicine, agriculture, and security).
Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers
Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks.
Multi-Source Unsupervised Domain Adaptation
Unsupervised Domain Adaptation
Less is More: Accelerating Faster Neural Networks Straight from JPEG
Most image data available are often stored in a compressed format, from which JPEG is the most widespread.
Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain
For this reason, a preliminary decoding process is required, since video data are often stored in a compressed format.
CNNs for JPEGs: A Study in Computational Cost
In this paper, we propose a further study of the computational cost of deep models designed for the frequency domain, evaluating the cost of decoding and passing the images through the network.
Low-Budget Label Query through Domain Alignment Enforcement
Deep learning revolution happened thanks to the availability of a massive amount of labelled data which have contributed to the development of models with extraordinary inference capabilities.
Multimedia Retrieval Through Unsupervised Hypergraph-Based Manifold Ranking
In this paper, a novel manifold ranking algorithm is proposed based on the hypergraphs for unsupervised multimedia retrieval tasks.
Bag of Attributes for Video Event Retrieval
This model is used to map low-level frame vectors into high-level vectors (e. g., classifier probability scores).
Bag of Genres for Video Retrieval
The Bag of Genres video vector contains a summary of the activations of each genre in the video content.
