Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification

• URL: http://arxiv.org/abs/2408.11237v1
• Date: Tue, 20 Aug 2024 23:30:00 GMT
• Title: Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification
• Authors: Christos Constantinou, Georgios Ioannides, Aman Chadha, Aaron Elkins, Edwin Simpson,
• Abstract summary: We propose a novel methodology termed as attention head masking (AHM) for multi-modal OOD tasks in document classification systems. Our empirical results demonstrate that the proposed AHM method outperforms all state-of-the-art approaches. To address the scarcity of high-quality publicly available document datasets, we introduce FinanceDocs, a new document AI dataset.
• Score: 3.141006099594433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detecting out-of-distribution (OOD) data is crucial in machine learning applications to mitigate the risk of model overconfidence, thereby enhancing the reliability and safety of deployed systems. The majority of existing OOD detection methods predominantly address uni-modal inputs, such as images or texts. In the context of multi-modal documents, there is a notable lack of extensive research on the performance of these methods, which have primarily been developed with a focus on computer vision tasks. We propose a novel methodology termed as attention head masking (AHM) for multi-modal OOD tasks in document classification systems. Our empirical results demonstrate that the proposed AHM method outperforms all state-of-the-art approaches and significantly decreases the false positive rate (FPR) compared to existing solutions up to 7.5\%. This methodology generalizes well to multi-modal data, such as documents, where visual and textual information are modeled under the same Transformer architecture. To address the scarcity of high-quality publicly available document datasets and encourage further research on OOD detection for documents, we introduce FinanceDocs, a new document AI dataset. Our code and dataset are publicly available.

Related papers

• What If the Input is Expanded in OOD Detection? [77.37433624869857]
  Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. We introduce a novel perspective, i.e., employing different common corruptions on the input space.
  arXiv  Detail & Related papers  (2024-10-24T06:47:28Z)
• MetaSumPerceiver: Multimodal Multi-Document Evidence Summarization for Fact-Checking [0.283600654802951]
  We present a summarization model designed to generate claim-specific summaries useful for fact-checking from multimodal datasets. We introduce a dynamic perceiver-based model that can handle inputs from multiple modalities of arbitrary lengths. Our approach outperforms the SOTA approach by 4.6% in the claim verification task on the MOCHEG dataset.
  arXiv  Detail & Related papers  (2024-07-18T01:33:20Z)
• A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection [52.228708947607636]
  This paper introduces a comprehensive visual anomaly detection benchmark, ADer, which is a modular framework for new methods. The benchmark includes multiple datasets from industrial and medical domains, implementing fifteen state-of-the-art methods and nine comprehensive metrics. We objectively reveal the strengths and weaknesses of different methods and provide insights into the challenges and future directions of multi-class visual anomaly detection.
  arXiv  Detail & Related papers  (2024-06-05T13:40:07Z)
• Out-of-Distribution Detection Using Peer-Class Generated by Large Language Model [0.0]
  Out-of-distribution (OOD) detection is a critical task to ensure the reliability and security of machine learning models. In this paper, a novel method called ODPC is proposed, in which specific prompts to generate OOD peer classes of ID semantics are designed by a large language model. Experiments on five benchmark datasets show that the method we propose can yield state-of-the-art results.
  arXiv  Detail & Related papers  (2024-03-20T06:04:05Z)
• Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection [67.68030805755679]
  Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class. In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs.
  arXiv  Detail & Related papers  (2023-10-12T04:14:28Z)
• Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability [70.72426887518517]
  Out-of-distribution (OOD) detection is an indispensable aspect of secure AI when deploying machine learning models in real-world applications. We propose a novel method, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data. Our method utilizes a mask to figure out the memorized atypical samples, and then finetune the model or prune it with the introduced mask to forget them.
  arXiv  Detail & Related papers  (2023-06-06T14:23:34Z)
• Do-GOOD: Towards Distribution Shift Evaluation for Pre-Trained Visual Document Understanding Models [68.12229916000584]
  We develop an out-of-distribution (OOD) benchmark termed Do-GOOD for the fine-Grained analysis on Document image-related tasks. We then evaluate the robustness and perform a fine-grained analysis of 5 latest VDU pre-trained models and 2 typical OOD generalization algorithms.
  arXiv  Detail & Related papers  (2023-06-05T06:50:42Z)
• Better Understanding Differences in Attribution Methods via Systematic Evaluations [57.35035463793008]
  Post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. We propose three novel evaluation schemes to more reliably measure the faithfulness of those methods. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods over a wide range of models.
  arXiv  Detail & Related papers  (2023-03-21T14:24:58Z)
• Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble [22.643719584452455]
  Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution. We propose a novel framework based on contrastive learning that encourages intermediate features to learn layer-specialized representations. Our approach is significantly more effective than other works.
  arXiv  Detail & Related papers  (2022-10-20T06:05:58Z)
• Igeood: An Information Geometry Approach to Out-of-Distribution Detection [35.04325145919005]
  We introduce Igeood, an effective method for detecting out-of-distribution (OOD) samples. Igeood applies to any pre-trained neural network, works under various degrees of access to the machine learning model. We show that Igeood outperforms competing state-of-the-art methods on a variety of network architectures and datasets.
  arXiv  Detail & Related papers  (2022-03-15T11:26:35Z)
• ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection [19.61846393392849]
  ProtoInfoMax is a new architecture that extends Prototypical Networks to simultaneously process In-Domain (ID) and OOD sentences. We show that our proposed method can substantially improve performance up to 20% for OOD detection in low resource settings.
  arXiv  Detail & Related papers  (2021-08-27T11:55:34Z)

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.