Performance Analysis of Out-of-Distribution Detection on Trained Neural Networks

• URL: http://arxiv.org/abs/2204.12378v1
• Date: Tue, 26 Apr 2022 15:24:38 GMT
• Title: Performance Analysis of Out-of-Distribution Detection on Trained Neural Networks
• Authors: Jens Henriksson, Christian Berger, Markus Borg, Lars Tornberg, Sankar Raman Sathyamoorthy, Cristofer Englund
• Abstract summary: We analyze three methods that separate between in- and out-of-distribution data, called supervisors, on four well-known Deep Learning architectures. We find that the outlier detection performance improves with the quality of the model. We observe that understanding the relationship between training results and supervisor performance is crucial to improve the model's robustness.
• Score: 8.934898793972879
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Several areas have been improved with Deep Learning during the past years. Implementing Deep Neural Networks (DNN) for non-safety related applications have shown remarkable achievements over the past years; however, for using DNNs in safety critical applications, we are missing approaches for verifying the robustness of such models. A common challenge for DNNs occurs when exposed to out-of-distribution samples that are outside of the scope of a DNN, but which result in high confidence outputs despite no prior knowledge of such input. In this paper, we analyze three methods that separate between in- and out-of-distribution data, called supervisors, on four well-known DNN architectures. We find that the outlier detection performance improves with the quality of the model. We also analyse the performance of the particular supervisors during the training procedure by applying the supervisor at a predefined interval to investigate its performance as the training proceeds. We observe that understanding the relationship between training results and supervisor performance is crucial to improve the model's robustness and to indicate, what input samples require further measures to improve the robustness of a DNN. In addition, our work paves the road towards an instrument for safety argumentation for safety critical applications. This paper is an extended version of our previous work presented at 2019 SEAA (cf. [1]); here, we elaborate on the used metrics, add an additional supervisor and test them on two additional datasets.

Related papers

• HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness [49.72591739116668]
  Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs)<n>However, prevalent methods like GRPO often fail when task difficulty exceeds the model's capacity, leading to reward sparsity and inefficient training.<n>We propose HINT: Helping Ineffective rollouts Navigate Towards effectiveness, an adaptive hinting framework.
  arXiv  Detail & Related papers  (2025-10-10T13:42:03Z)
• DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis [1.7266027274320124]
  DeepProv is a system designed to capture and characterize the runtime behavior of Deep neural networks (DNNs) during inference.<n>Inspired by system audit provenance graphs, DeepProv models the computational information flow of a DNN's inference process through Inference Provenance Graphs (IPGs)<n>DeepProv uses these insights to systematically repair DNNs for specific objectives, such as improving robustness, privacy, or fairness.
  arXiv  Detail & Related papers  (2025-09-30T17:29:02Z)
• Test-time Offline Reinforcement Learning on Goal-related Experience [50.94457794664909]
  Research in foundation models has shown that performance can be substantially improved through test-time training.<n>We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state.<n>Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out.
  arXiv  Detail & Related papers  (2025-07-24T21:11:39Z)
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [89.54947228958494]
  This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework. TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
  arXiv  Detail & Related papers  (2023-03-20T14:12:55Z)
• Iterative Assessment and Improvement of DNN Operational Accuracy [11.447394702830412]
  We propose DAIC (DNN Assessment and Improvement Cycle), an approach which combines ''low-cost'' online pseudo-oracles and ''high-cost'' offline sampling techniques. Preliminary results show the benefits of combining the two approaches.
  arXiv  Detail & Related papers  (2023-03-02T14:21:54Z)
• Cross-Modal Fine-Tuning: Align then Refine [83.37294254884446]
  ORCA is a cross-modal fine-tuning framework that extends the applicability of a single large-scale pretrained model to diverse modalities. We show that ORCA obtains state-of-the-art results on 3 benchmarks containing over 60 datasets from 12 modalities.
  arXiv  Detail & Related papers  (2023-02-11T16:32:28Z)
• Composite Learning for Robust and Effective Dense Predictions [81.2055761433725]
  Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. We find that jointly training a dense prediction (target) task with a self-supervised (auxiliary) task can consistently improve the performance of the target task, while eliminating the need for labeling auxiliary tasks.
  arXiv  Detail & Related papers  (2022-10-13T17:59:16Z)
• Out-of-Distribution Detection with Hilbert-Schmidt Independence Optimization [114.43504951058796]
  Outlier detection tasks have been playing a critical role in AI safety. Deep neural network classifiers usually tend to incorrectly classify out-of-distribution (OOD) inputs into in-distribution classes with high confidence. We propose an alternative probabilistic paradigm that is both practically useful and theoretically viable for the OOD detection tasks.
  arXiv  Detail & Related papers  (2022-09-26T15:59:55Z)
• An Intrusion Detection System based on Deep Belief Networks [1.535077825808595]
  We develop and evaluate the performance of DBN on detecting cyber-attacks within a network of connected devices. Our proposed DBN approach shows competitive and promising results, with significant improvement on the detection of attacks underrepresented in the training dataset.
  arXiv  Detail & Related papers  (2022-07-05T15:38:24Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• RoMA: Robust Model Adaptation for Offline Model-based Optimization [115.02677045518692]
  We consider the problem of searching an input maximizing a black-box objective function given a static dataset of input-output queries. A popular approach to solving this problem is maintaining a proxy model that approximates the true objective function. Here, the main challenge is how to avoid adversarially optimized inputs during the search.
  arXiv  Detail & Related papers  (2021-10-27T05:37:12Z)
• Performance Analysis of Out-of-Distribution Detection on Various Trained Neural Networks [12.22753756637137]
  A common challenge for Deep Neural Networks (DNN) occur when exposed to out-of-distribution samples that are previously unseen. In this paper we analyse two supervisors on two well-known DNNs with varied setups of training. We find that the outlier detection performance improves with the quality of the training procedure.
  arXiv  Detail & Related papers  (2021-03-29T12:52:02Z)
• Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks [32.629801680158685]
  Sketching Curvature of OoD Detection (SCOD) is an architecture-agnostic framework for equipping trained Deep Neural Networks with task-relevant uncertainty estimates. We demonstrate that SCOD achieves comparable or better OoD detection performance with lower computational burden relative to existing baselines.
  arXiv  Detail & Related papers  (2021-02-24T21:34:40Z)
• Designing Interpretable Approximations to Deep Reinforcement Learning [14.007731268271902]
  Deep neural networks (DNNs) set the bar for algorithm performance. It may not be feasible to actually use such high-performing DNNs in practice. This work seeks to identify reduced models that not only preserve a desired performance level, but also, for example, succinctly explain the latent knowledge represented by a DNN.
  arXiv  Detail & Related papers  (2020-10-28T06:33:09Z)

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.