The Open-World Lottery Ticket Hypothesis for OOD Intent Classification

• URL: http://arxiv.org/abs/2210.07071v3
• Date: Wed, 24 Apr 2024 02:37:55 GMT
• Title: The Open-World Lottery Ticket Hypothesis for OOD Intent Classification
• Authors: Yunhua Zhou, Pengyu Wang, Peiju Liu, Yuxin Wang, Xipeng Qiu,
• Abstract summary: We shed light on the fundamental cause of model overconfidence on OOD. We also extend the Lottery Ticket Hypothesis to open-world scenarios.
• Score: 68.93357975024773
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most existing methods of Out-of-Domain (OOD) intent classification rely on extensive auxiliary OOD corpora or specific training paradigms. However, they are underdeveloped in the underlying principle that the models should have differentiated confidence in In- and Out-of-domain intent. In this work, we shed light on the fundamental cause of model overconfidence on OOD and demonstrate that calibrated subnetworks can be uncovered by pruning the overparameterized model. Calibrated confidence provided by the subnetwork can better distinguish In- and Out-of-domain, which can be a benefit for almost all post hoc methods. In addition to bringing fundamental insights, we also extend the Lottery Ticket Hypothesis to open-world scenarios. We conduct extensive experiments on four real-world datasets to demonstrate our approach can establish consistent improvements compared with a suite of competitive baselines.

Related papers

• Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation [4.506099292980221]
  We evaluate and analyze the OoDD capabilities of various proprietary and open-source LVLMs. We propose a self-guided prompting approach, termed emphReflexive Guidance (ReGuide), aimed at enhancing the OoDD capability of LVLMs. Experimental results demonstrate that our ReGuide enhances the performance of current LVLMs in both image classification and OoDD tasks.
  arXiv  Detail & Related papers  (2024-10-19T04:46:51Z)
• High-Performance Few-Shot Segmentation with Foundation Models: An Empirical Study [64.06777376676513]
  We develop a few-shot segmentation (FSS) framework based on foundation models. To be specific, we propose a simple approach to extract implicit knowledge from foundation models to construct coarse correspondence. Experiments on two widely used datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-09-10T08:04:11Z)
• WeiPer: OOD Detection using Weight Perturbations of Class Projections [11.130659240045544]
  We introduce perturbations of the class projections in the final fully connected layer which creates a richer representation of the input. We achieve state-of-the-art OOD detection results across multiple benchmarks of the OpenOOD framework.
  arXiv  Detail & Related papers  (2024-05-27T13:38:28Z)
• Towards Context-Aware Domain Generalization: Understanding the Benefits and Limits of Marginal Transfer Learning [1.5320861212113897]
  We formalize the notion of context as a permutation-invariant representation of a set of data points. Empirical analysis shows that our criteria are effective in discerning both favorable and unfavorable scenarios.
  arXiv  Detail & Related papers  (2023-12-15T05:18:07Z)
• Towards Calibrated Robust Fine-Tuning of Vision-Language Models [97.19901765814431]
  This work proposes a robust fine-tuning method that improves both OOD accuracy and confidence calibration simultaneously in vision language models. We show that both OOD classification and OOD calibration errors have a shared upper bound consisting of two terms of ID data. Based on this insight, we design a novel framework that conducts fine-tuning with a constrained multimodal contrastive loss enforcing a larger smallest singular value.
  arXiv  Detail & Related papers  (2023-11-03T05:41:25Z)
• Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly [79.07074710460012]
  adversarial vulnerability of deep neural networks (DNNs) has drawn great attention. An increasing number of transfer-based methods have been developed to fool black-box DNN models. We establish a transfer-based attack benchmark (TA-Bench) which implements 30+ methods.
  arXiv  Detail & Related papers  (2023-11-02T15:35:58Z)
• Generalizability of Adversarial Robustness Under Distribution Shifts [57.767152566761304]
  We take a first step towards investigating the interplay between empirical and certified adversarial robustness on one hand and domain generalization on another. We train robust models on multiple domains and evaluate their accuracy and robustness on an unseen domain. We extend our study to cover a real-world medical application, in which adversarial augmentation significantly boosts the generalization of robustness with minimal effect on clean data accuracy.
  arXiv  Detail & Related papers  (2022-09-29T18:25:48Z)
• WeShort: Out-of-distribution Detection With Weak Shortcut structure [0.0]
  We propose a simple and effective post-hoc technique, WeShort, to reduce the overconfidence of neural networks on OOD data. Our method is compatible with different OOD detection scores and can generalize well to different architectures of networks.
  arXiv  Detail & Related papers  (2022-06-23T07:59:10Z)
• Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU [70.44344060176952]
  Intent classification is a major task in spoken language understanding (SLU) Recent works have shown that using extra data and labels can improve the OOD detection performance. This paper proposes to train a model with only IND data while supporting both IND intent classification and OOD detection.
  arXiv  Detail & Related papers  (2021-06-28T08:27:38Z)
• Confidence Estimation via Auxiliary Models [47.08749569008467]
  We introduce a novel target criterion for model confidence, namely the true class probability ( TCP) We show that TCP offers better properties for confidence estimation than standard maximum class probability (MCP)
  arXiv  Detail & Related papers  (2020-12-11T17:21:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.