5 papers
Query-Conditioned Prototype Adaptation for Cross-Domain Few-Shot Learning: Single-Query Inference, Controlled Comparisons, and Failure Modes
Rushab Rasik Karania, Tomas Maul
Cross-domain few-shot learning requires adapting a classifier to a new visual domain from very few labelled examples without target-time parameter updates. We isolate one question:…
AMAuT: A Flexible and Efficient Multiview Audio Transformer Framework Trained from Scratch
Weichuang Shao, Iman Yi Liao, Tomas Henrique Bode Maul +1
Recent foundational models, SSAST, EAT, HuBERT, Qwen-Audio, and Audio Flamingo, achieve top-tier results across standard audio benchmarks but are limited by fixed input rates and d…
DHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation
Weichuang Shao, Iman Yi Liao, Tomas Henrique Bode Maul +1
Existing Test-time Adaptation (TTA) studies rely heavily on static and homogeneous corruption protocols, such as ImageNet-C and CIFAR-10-C/100-C, leading to inconsistent evaluation…
An Investigation of Test-time Adaptation for Audio Classification under Background Noise
Weichuang Shao, Iman Yi Liao, Tomas Henrique Bode Maul +1
Domain shift is a prominent problem in Deep Learning, causing a model pre-trained on a source dataset to suffer significant performance degradation on test datasets. This research…
Balancing Accuracy and Latency in Multipath Neural Networks
Mohammed Amer, Tomás Maul, Iman Yi Liao
The growing capacity of neural networks has strongly contributed to their success at complex machine learning tasks and the computational demand of such large models has, in turn,…