Search Results for author:
Found 10 papers, 8 papers with code
A Closer Look at Few-Shot Out-of-Distribution Intent Detection
Comprehensive experiments on three real-world intent detection benchmark datasets demonstrate the high effectiveness of our proposed approach and its great potential in improving state-of-the-art methods for few-shot OOD intent detection.
VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection
Out-of-distribution (OOD) detection plays a crucial role in ensuring the safety and reliability of deep neural networks in various applications.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+4
New Intent Discovery with Pre-training and Contrastive Learning
Existing approaches typically rely on a large amount of labeled utterances and employ pseudo-labeling methods for representation learning and clustering, which are label-intensive, inefficient, and inaccurate.
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima
Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting.
Ranked #7 on
Few-Shot Class-Incremental Learning
on mini-Imagenet
Effectiveness of Pre-training for Few-shot Intent Classification
This paper investigates the effectiveness of pre-training for few-shot intent classification.
Adaptation-Agnostic Meta-Training
Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters are updated during meta-update.
Out-of-Scope Intent Detection with Self-Supervision and Discriminative Training
Since the distribution of outlier utterances is arbitrary and unknown in the training stage, existing methods commonly rely on strong assumptions on data distribution such as mixture of Gaussians to make inference, resulting in either complex multi-step training procedures or hand-crafted rules such as confidence threshold selection for outlier detection.
SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering
We show that SLAKE can be used to facilitate the development and evaluation of Med-VQA systems.
A Closer Look at the Training Strategy for Modern Meta-Learning
The support/query (S/Q) episodic training strategy has been widely used in modern meta-learning algorithms and is believed to improve their generalization ability to test environments.
Variational Metric Scaling for Metric-Based Meta-Learning
In this paper, we recast metric-based meta-learning from a Bayesian perspective and develop a variational metric scaling framework for learning a proper metric scaling parameter.
