5 papers
A-TPT: Angular Diversity Calibration Properties for Test-Time Prompt Tuning of Vision-Language Models
Shihab Aaqil Ahamed, Udaya S. K. P. Miriya Thanthrige, Ranga Rodrigo +1
Test-time prompt tuning (TPT) has emerged as a promising technique for adapting large vision-language models (VLMs) to unseen tasks without relying on labeled data. However, the la…
Radar and Acoustic Sensor Fusion using a Transformer Encoder for Robust Drone Detection and Classification
Gevindu Ganganath, Pasindu Sankalpa, Samal Punsara +4
The use of drones in a wide range of applications is steadily increasing. However, this has also raised critical security concerns such as unauthorized drone intrusions into restri…
Uncertainty Awareness Enables Efficient Labeling for Cancer Subtyping in Digital Pathology
Nirhoshan Sivaroopan, Chamuditha Jayanga Galappaththige, Chalani Ekanayake +4
Machine-learning-assisted cancer subtyping is a promising avenue in digital pathology. Cancer subtyping models, however, require careful training using expert annotations so that t…
SATHUR: Self Augmenting Task Hallucinal Unified Representation for Generalized Class Incremental Learning
Sathursan Kanagarajah, Thanuja Ambegoda, Ranga Rodrigo
Class Incremental Learning (CIL) is inspired by the human ability to learn new classes without forgetting previous ones. CIL becomes more challenging in real-world scenarios when t…
Contrastive Deep Encoding Enables Uncertainty-aware Machine-learning-assisted Histopathology
Nirhoshan Sivaroopan, Chamuditha Jayanga, Chalani Ekanayake +6
Deep neural network models can learn clinically relevant features from millions of histopathology images. However generating high-quality annotations to train such models for each…