Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection

• URL: http://arxiv.org/abs/2510.05782v2
• Date: Sun, 19 Oct 2025 14:04:33 GMT
• Title: Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection
• Authors: I. M. De la Jara, C. Rodriguez-Opazo, D. Teney, D. Ranasinghe, E. Abbasnejad,
• Abstract summary: Methods treat large pre-trained models as monolithic encoders and rely solely on their final-layer representations for detection.<n>We reveal the textitintermediate layers of pre-trained models, shaped by residual connections that subtly transform input projections.<n>We show that selectively incorporating these intermediate representations can increase the accuracy of OOD detection by up to textbf$10%$ in far-OOD and over textbf$7%$ in near-OOD benchmarks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Out-of-distribution (OOD) detection is essential for reliably deploying machine learning models in the wild. Yet, most methods treat large pre-trained models as monolithic encoders and rely solely on their final-layer representations for detection. We challenge this wisdom. We reveal the \textit{intermediate layers} of pre-trained models, shaped by residual connections that subtly transform input projections, \textit{can} encode \textit{surprisingly rich and diverse signals} for detecting distributional shifts. Importantly, to exploit latent representation diversity across layers, we introduce an entropy-based criterion to \textit{automatically} identify layers offering the most complementary information in a training-free setting -- \textit{without access to OOD data}. We show that selectively incorporating these intermediate representations can increase the accuracy of OOD detection by up to \textbf{$10\%$} in far-OOD and over \textbf{$7\%$} in near-OOD benchmarks compared to state-of-the-art training-free methods across various model architectures and training objectives. Our findings reveal a new avenue for OOD detection research and uncover the impact of various training objectives and model architectures on confidence-based OOD detection methods.

Related papers

• Revisiting Logit Distributions for Reliable Out-of-Distribution Detection [73.9121001113687]
  Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning models in open-world applications.<n>LogitGap is a novel post-hoc OOD detection method that exploits the relationship between the maximum logit and the remaining logits.<n>We show that LogitGap consistently achieves state-of-the-art performance across diverse OOD detection scenarios and benchmarks.
  arXiv  Detail & Related papers  (2025-10-23T02:16:45Z)
• RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations [33.971901643313856]
  RUNA is a novel framework for detecting out-of-distribution (OOD) objects.<n>It employs a regional uncertainty alignment mechanism to distinguish ID from OOD objects effectively.<n>Our experiments show that RUNA substantially surpasses state-of-the-art methods in object-level OOD detection.
  arXiv  Detail & Related papers  (2025-03-28T10:01:55Z)
• Can OOD Object Detectors Learn from Foundation Models? [56.03404530594071]
  Out-of-distribution (OOD) object detection is a challenging task due to the absence of open-set OOD data. Inspired by recent advancements in text-to-image generative models, we study the potential of generative models trained on large-scale open-set data to synthesize OOD samples. We introduce SyncOOD, a simple data curation method that capitalizes on the capabilities of large foundation models.
  arXiv  Detail & Related papers  (2024-09-08T17:28:22Z)
• Logit Scaling for Out-of-Distribution Detection [13.017887434494373]
  We propose a simple, post-hoc method that does not require access to the training data distribution.<n>Our method, Logit Scaling (LTS), scales the logits in a manner that effectively distinguishes between in-distribution (ID) and OOD samples.<n>We tested our method on benchmarks across various scales, including CIFAR-10, CIFAR-100, ImageNet and OpenOOD.
  arXiv  Detail & Related papers  (2024-09-02T11:10:44Z)
• 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)
• GROOD: GRadient-Aware Out-of-Distribution Detection [11.511906612904255]
  Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models in real-world applications.<n>We propose GRadient-aware Out-Of-Distribution detection (GROOD), a method that derives an OOD prototype from synthetic samples and computes class prototypes directly from In-distribution (ID) training data.
  arXiv  Detail & Related papers  (2023-12-22T04:28:43Z)
• EAT: Towards Long-Tailed Out-of-Distribution Detection [55.380390767978554]
  This paper addresses the challenging task of long-tailed OOD detection. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes. We propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes, and (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data.
  arXiv  Detail & Related papers  (2023-12-14T13:47:13Z)
• A Mixture of Exemplars Approach for Efficient Out-of-Distribution Detection with Foundation Models [0.0]
  This paper presents an efficient approach to tackling OOD detection that is designed to maximise the benefit of training a backbone with a high quality, frozen, pretrained foundation model.<n>MoLAR provides strong OOD detection performance when only comparing the similarity of OOD examples to the exemplars, a small set of images chosen to be representative of the dataset.
  arXiv  Detail & Related papers  (2023-11-28T06:12:28Z)
• From Global to Local: Multi-scale Out-of-distribution Detection [129.37607313927458]
  Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation learning gives rise to distance-based OOD detection. We propose Multi-scale OOD DEtection (MODE), a first framework leveraging both global visual information and local region details.
  arXiv  Detail & Related papers  (2023-08-20T11:56:25Z)
• 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)
• Improving Out-of-Distribution Detection with Disentangled Foreground and Background Features [23.266183020469065]
  We propose a novel framework that disentangles foreground and background features from ID training samples via a dense prediction approach. It is a generic framework that allows for a seamless combination with various existing OOD detection methods.
  arXiv  Detail & Related papers  (2023-03-15T16:12:14Z)
• 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)
• Pseudo-OOD training for robust language models [78.15712542481859]
  OOD detection is a key component of a reliable machine-learning model for any industry-scale application. We propose POORE - POsthoc pseudo-Ood REgularization, that generates pseudo-OOD samples using in-distribution (IND) data. We extensively evaluate our framework on three real-world dialogue systems, achieving new state-of-the-art in OOD detection.
  arXiv  Detail & Related papers  (2022-10-17T14:32:02Z)
• 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)
• 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)

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.