Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition

• URL: http://arxiv.org/abs/2606.24404v1
• Date: Tue, 23 Jun 2026 10:39:04 GMT
• Title: Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition
• Abstract summary: We study how to incorporate additional modalities into action recognition models.<n>This work focuses on the case of multi-modal out-of-distribution (OOD) detection.<n>We build a post-hoc detector explicitly designed for the multi-modal scenario.
• Score: 23.03076857904803
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The incorporation of additional modalities into action recognition models increases their performance across a wide range of settings. However, how this additional information can contribute to making the models more robust remains underexplored, particularly for the case of multi-modal out-of-distribution (OOD) detection. While methods exist that regularize the multi-modal training process with OOD detection in mind, they still apply off-the-shelf OOD detectors designed for the uni-modal case during inference, discarding important information. Based on an interesting relationship we find between the multi-modal and uni-modal predictions, we propose to use this signal to build a post-hoc detector explicitly designed for the multi-modal scenario. We combine this new source of information with a feature-space score, which detects off-manifold samples in the multi-modal space, and normalize them by the multi-modal logits. In doing so, the proposed hybrid detector is compatible with existing training-time approaches and consistently improves performance. Experiments on a wide range of established datasets from the MultiOOD benchmark show that, on average, our approach outperforms the state of the art. Our results show the importance of explicitly considering the different modalities at inference time for multi-modal OOD detection.

Related papers

• MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering [73.47440561592556]
  We introduce MultAttnAttrib, a training-free attribution-generation method.<n>We show that MultAttnAttrib consistently outperforms a variety of attribution-generation methods.<n>Our method produces attributions at up to one-seventh of the direct inference latency compared to prompting.
  arXiv  Detail & Related papers  (2026-07-01T19:29:19Z)
• POINTS-Seeker: Towards Training a Multimodal Agentic Search Model from Scratch [84.73366911912512]
  We introduce Agentic Seeding, a dedicated phase designed to weave the precursors necessary for eliciting agentic behaviors.<n>We propose V-Fold, an adaptive history-aware compression scheme that preserves recent dialogue turns in high fidelity while folding historical context into the visual space via rendering.<n>We develop POINTS-Seeker-8B, a state-of-the-art multimodal agentic search model that consistently outperforms existing models across six diverse benchmarks.
  arXiv  Detail & Related papers  (2026-04-15T16:09:37Z)
• Active Multimodal Distillation for Few-shot Action Recognition [19.872938560809988]
  This paper presents a novel framework that actively identifies reliable modalities for each sample using task-specific contextual cues.<n>Our framework integrates an Active Sample Inference (ASI) module, which utilizes active inference to predict reliable modalities.<n>Unlike reinforcement learning, active inference replaces rewards with evidence-based preferences, making more stable predictions.
  arXiv  Detail & Related papers  (2025-06-16T10:10:56Z)
• Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation [7.827311520283545]
  Out-of-distribution (OOD) detection and segmentation are crucial for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery.<n>We propose Feature Mixing, an extremely simple and fast method for multimodal outlier synthesis with theoretical support.<n>We introduce CARLA-OOD, a novel multimodal dataset for OOD segmentation, featuring synthetic OOD objects across diverse scenes and weather conditions.
  arXiv  Detail & Related papers  (2025-05-22T17:54:30Z)
• MIND: Modality-Informed Knowledge Distillation Framework for Multimodal Clinical Prediction Tasks [50.98856172702256]
  We propose the Modality-INformed knowledge Distillation (MIND) framework, a multimodal model compression approach.<n>MIND transfers knowledge from ensembles of pre-trained deep neural networks of varying sizes into a smaller multimodal student.<n>We evaluate MIND on binary and multilabel clinical prediction tasks using time series data and chest X-ray images.
  arXiv  Detail & Related papers  (2025-02-03T08:50:00Z)
• DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection [10.834698906236405]
  Out-of-distribution (OOD) detection is essential for ensuring the robustness of machine learning models. Recent advances in multimodal models have demonstrated the potential of leveraging multiple modalities to enhance detection performance. We propose Dynamic Prototype Updating (DPU), a novel plug-and-play framework for multimodal OOD detection.
  arXiv  Detail & Related papers  (2024-11-12T22:43:16Z)
• MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities [11.884004583641325]
  We introduce the first-of-its-kind benchmark, MultiOOD, characterized by diverse dataset sizes and varying modality combinations. We first evaluate existing unimodal OOD detection algorithms on MultiOOD, observing that the mere inclusion of additional modalities yields substantial improvements. We introduce a novel outlier synthesis method, NP-Mix, which explores broader feature spaces by leveraging the information from nearest neighbor classes.
  arXiv  Detail & Related papers  (2024-05-27T17:59:02Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications [90.6849884683226]
  We study the challenge of interaction quantification in a semi-supervised setting with only labeled unimodal data. Using a precise information-theoretic definition of interactions, our key contribution is the derivation of lower and upper bounds. We show how these theoretical results can be used to estimate multimodal model performance, guide data collection, and select appropriate multimodal models for various tasks.
  arXiv  Detail & Related papers  (2023-06-07T15:44:53Z)
• Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework [89.8609061423685]
  We propose an information-theoretic approach to quantify the degree of redundancy, uniqueness, and synergy relating input modalities with an output task. To validate PID estimation, we conduct extensive experiments on both synthetic datasets where the PID is known and on large-scale multimodal benchmarks. We demonstrate their usefulness in (1) quantifying interactions within multimodal datasets, (2) quantifying interactions captured by multimodal models, (3) principled approaches for model selection, and (4) three real-world case studies.
  arXiv  Detail & Related papers  (2023-02-23T18:59:05Z)
• SHAPE: An Unified Approach to Evaluate the Contribution and Cooperation of Individual Modalities [7.9602600629569285]
  We use bf SHapley vbf Alue-based bf PErceptual (SHAPE) scores to measure the marginal contribution of individual modalities and the degree of cooperation across modalities. Our experiments suggest that for some tasks where different modalities are complementary, the multi-modal models still tend to use the dominant modality alone. We hope our scores can help improve the understanding of how the present multi-modal models operate on different modalities and encourage more sophisticated methods of integrating multiple modalities.
  arXiv  Detail & Related papers  (2022-04-30T16:35:40Z)

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.