Leveraging Intermediate Representations for Better Out-of-Distribution Detection

• URL: http://arxiv.org/abs/2502.12849v1
• Date: Tue, 18 Feb 2025 13:38:19 GMT
• Title: Leveraging Intermediate Representations for Better Out-of-Distribution Detection
• Authors: Gianluca Guglielmo, Marc Masana,
• Abstract summary: In real-world applications, machine learning models must reliably detect Out-of-Distribution (OoD) samples to prevent unsafe decisions. We analyze the discriminative power of intermediate layers and show that they can positively be used for OoD detection. We demonstrate that intermediate layer activations improves OoD detection performance by running a comprehensive evaluation across multiple datasets.
• Score: 3.903824667492754
• License:
• Abstract: In real-world applications, machine learning models must reliably detect Out-of-Distribution (OoD) samples to prevent unsafe decisions. Current OoD detection methods often rely on analyzing the logits or the embeddings of the penultimate layer of a neural network. However, little work has been conducted on the exploitation of the rich information encoded in intermediate layers. To address this, we analyze the discriminative power of intermediate layers and show that they can positively be used for OoD detection. Therefore, we propose to regularize intermediate layers with an energy-based contrastive loss, and by grouping multiple layers in a single aggregated response. We demonstrate that intermediate layer activations improves OoD detection performance by running a comprehensive evaluation across multiple datasets.

Related papers

• Beyond Perceptual Distances: Rethinking Disparity Assessment for Out-of-Distribution Detection with Diffusion Models [28.96695036746856]
  Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection. DM-based methods bring fresh insights to the field, yet remain under-explored. Our work has demonstrated state-of-the-art detection performances among DM-based methods in extensive experiments.
  arXiv  Detail & Related papers  (2024-09-16T08:50:47Z)
• Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark [73.58840254552656]
  Unsupervised graph-level anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection have received significant attention in recent years. We present a Unified Benchmark for unsupervised Graph-level OOD and anomaly Detection (our method) Our benchmark encompasses 35 datasets spanning four practical anomaly and OOD detection scenarios. We conduct multi-dimensional analyses to explore the effectiveness, generalizability, robustness, and efficiency of existing methods.
  arXiv  Detail & Related papers  (2024-06-21T04:07:43Z)
• A Functional Data Perspective and Baseline On Multi-Layer Out-of-Distribution Detection [30.499548939422194]
  Methods that explore the multiple layers either require a special architecture or a supervised objective to do so. This work adopts an original approach based on a functional view of the network that exploits the sample's trajectories through the various layers and their statistical dependencies. We validate our method and empirically demonstrate its effectiveness in OOD detection compared to strong state-of-the-art baselines on computer vision benchmarks.
  arXiv  Detail & Related papers  (2023-06-06T09:14:05Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• Benchmarking Deep Models for Salient Object Detection [67.07247772280212]
  We construct a general SALient Object Detection (SALOD) benchmark to conduct a comprehensive comparison among several representative SOD methods. In the above experiments, we find that existing loss functions usually specialized in some metrics but reported inferior results on the others. We propose a novel Edge-Aware (EA) loss that promotes deep networks to learn more discriminative features by integrating both pixel- and image-level supervision signals.
  arXiv  Detail & Related papers  (2022-02-07T03:43:16Z)
• Class-wise Thresholding for Detecting Out-of-Distribution Data [6.5295089440496055]
  We consider the problem of detecting OoD(Out-of-Distribution) input data when using deep neural networks. We propose a class-wise thresholding scheme that can apply to most existing OoD detection algorithms.
  arXiv  Detail & Related papers  (2021-10-28T16:54:48Z)
• Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation [76.2621758731288]
  We tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA) We show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.
  arXiv  Detail & Related papers  (2021-08-03T17:09:56Z)
• Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation [7.305019142196585]
  "Out-of-distribution" (OoD) samples are crucial for many applications such as automated driving. A natural baseline approach to OoD detection is to threshold on the pixel-wise softmax entropy. We present a two-step procedure that significantly improves that approach.
  arXiv  Detail & Related papers  (2020-12-09T11:01:06Z)
• A General Framework For Detecting Anomalous Inputs to DNN Classifiers [37.79389209020564]
  We propose an unsupervised anomaly detection framework based on the internal deep neural network layer representations. We evaluate the proposed methods on well-known image classification datasets with strong adversarial attacks and OOD inputs.
  arXiv  Detail & Related papers  (2020-07-29T22:57:57Z)
• Understanding and Diagnosing Vulnerability under Adversarial Attacks [62.661498155101654]
  Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks. We propose a novel interpretability method, InterpretGAN, to generate explanations for features used for classification in latent variables. We also design the first diagnostic method to quantify the vulnerability contributed by each layer.
  arXiv  Detail & Related papers  (2020-07-17T01:56:28Z)
• BiDet: An Efficient Binarized Object Detector [96.19708396510894]
  We propose a binarized neural network learning method called BiDet for efficient object detection. Our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal. Our method outperforms the state-of-the-art binary neural networks by a sizable margin.
  arXiv  Detail & Related papers  (2020-03-09T08:16:16Z)

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.