Related papers: SpurAudio: A Benchmark for Studying Shortcut Learn…
Proprietary and closed APIs are becoming increasingly common to process natural language, and are impacting the practical applications of natural language processing, including few-shot classification. Few-shot classification involves…
Anomaly detection has many important applications, such as monitoring industrial equipment. Despite recent advances in anomaly detection with deep-learning methods, it is unclear how existing solutions would perform under…
The high cost of data labeling presents a major barrier to deploying machine learning systems at scale. Semi-supervised learning (SSL) mitigates this challenge by utilizing unlabeled data alongside limited labeled examples, while the…
Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images. The current correlation-based methods construct pair-wise feature correlations to…
Few-shot learning benchmarks are critical for evaluating modern NLP techniques. It is possible, however, that benchmarks favor methods which easily make use of unlabeled text, because researchers can use unlabeled text from the test set to…
Acoustic scene classification (ASC) predominantly relies on supervised approaches. However, acquiring labeled data for training ASC models is often costly and time-consuming. Recently, self-supervised learning (SSL) has emerged as a…
Learning from a limited amount of data, namely Few-Shot Learning, stands out as a challenging computer vision task. Several works exploit semantics and design complicated semantic fusion mechanisms to compensate for rare representative…
Recent work has shown that label-efficient few-shot learning through self-supervision can achieve promising medical image segmentation results. However, few-shot segmentation models typically rely on prototype representations of the…
Remote sensing applications increasingly rely on deep learning for scene classification. However, their performance is often constrained by the scarcity of labeled data and the high cost of annotation across diverse geographic and sensor…
In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified. We first present a general purpose…
In machine learning applications, gradual data ingress is common, especially in audio processing where incremental learning is vital for real-time analytics. Few-shot class-incremental learning addresses challenges arising from limited…
The existing event classification (EC) work primarily focuseson the traditional supervised learning setting in which models are unableto extract event mentions of new/unseen event types. Few-shot learninghas not been investigated in this…
This paper presents a context-aware framework for feature selection and classification procedures to realize a fast and accurate audio event annotation and classification. The context-aware design starts with exploring feature extraction…
Automatic Speech Recognition (ASR) in professional settings faces challenges that existing benchmarks underplay: dense domain terminology, formal register variation, and near-zero tolerance for critical entity errors. We present…
Few-shot dialogue state tracking (DST) is a realistic problem that trains the DST model with limited labeled data. Existing few-shot methods mainly transfer knowledge learned from external labeled dialogue data (e.g., from question…
Few-shot classification involves identifying new categories using a limited number of labeled samples. Current few-shot classification methods based on local descriptors primarily leverage underlying consistent features across visible and…
A model that avoids stereotypes in a lab benchmark may not avoid them in deployment. We show that measured bias shifts dramatically when prompts mention different places, times, or audiences -- no adversarial prompting required. We…
The existing barely-supervised medical image segmentation (BSS) methods, adopting a registration-segmentation paradigm, aim to learn from data with very few annotations to mitigate the extreme label scarcity problem. However, this paradigm…
Text and vision foundation models can perform many tasks in a zero-shot setting, a desirable property that enables these systems to be applied in general and low-resource settings. There has been far less work, however, on the zero-shot…
Semi-supervised few-shot learning (SSFSL) formulates real-world applications like ''auto-annotation'', as it aims to learn a model over a few labeled and abundant unlabeled examples to annotate the unlabeled ones. Despite the availability…