Tuned Reverse Distillation: Enhancing Multimodal Industrial Anomaly Detection with Crossmodal Tuners

• URL: http://arxiv.org/abs/2412.08949v3
• Date: Fri, 25 Jul 2025 11:10:39 GMT
• Title: Tuned Reverse Distillation: Enhancing Multimodal Industrial Anomaly Detection with Crossmodal Tuners
• Authors: Xinyue Liu, Jianyuan Wang, Biao Leng, Shuo Zhang,
• Abstract summary: We propose Tuned Reverse Distillation (TRD) based on Multi-branch design to realize Multimodal Industrial AD.<n>By assigning independent branches to each modality, our method enables finer detection of anomalies within each modality.<n>Our method achieves state-of-the-art performance in multimodal anomaly detection and localization.
• Score: 15.89869857998053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge distillation (KD) has been widely studied in unsupervised image Anomaly Detection (AD), but its application to unsupervised multimodal AD remains underexplored. Existing KD-based methods for multimodal AD that use fused multimodal features to obtain teacher representations face challenges. Anomalies that only exist in one modality may not be effectively captured in the fused teacher features, leading to detection failures. Besides, these methods do not fully leverage the rich intra- and inter-modality information that are critical for effective anomaly detection. In this paper, we propose Tuned Reverse Distillation (TRD) based on Multi-branch design to realize Multimodal Industrial AD. By assigning independent branches to each modality, our method enables finer detection of anomalies within each modality. Furthermore, we enhance the interaction between modalities during the distillation process by designing two Crossmodal Tuners including Crossmodal Filter and Amplifier. With the idea of crossmodal mapping, the student network is allowed to better learn normal features while anomalies in all modalities are ensured to be effectively detected. Experimental verifications on multimodal AD datasets demonstrate that our method achieves state-of-the-art performance in multimodal anomaly detection and localization. Code is available at https://github.com/hito2448/TRD.

Related papers

• 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. MIND transfers knowledge from ensembles of pre-trained deep neural networks of varying sizes into a smaller multimodal student. 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)
• RADAR: Robust Two-stage Modality-incomplete Industrial Anomaly Detection [61.71770293720491]
  We propose a novel two-stage Robust modAlity-imcomplete fusing and Detecting frAmewoRk, abbreviated as RADAR. Our bootstrapping philosophy is to enhance two stages in MIIAD, improving the robustness of the Multimodal Transformer. Our experimental results demonstrate that the proposed RADAR significantly surpasses conventional MIAD methods in terms of effectiveness and robustness.
  arXiv  Detail & Related papers  (2024-10-02T16:47:55Z)
• Incomplete Multimodal Industrial Anomaly Detection via Cross-Modal Distillation [0.0]
  multimodal industrial anomaly detection (IAD) based on 3D point clouds and RGB images remains a work in progress. Existing quality control processes combine rapid in-line inspections, such as optical and infrared imaging with high-resolution but time-consuming near-line characterization techniques. We propose CMDIAD, a Cross-Modal Distillation framework for IAD to demonstrate the feasibility of a Multi-modal Training, Few-modal Inference pipeline.
  arXiv  Detail & Related papers  (2024-05-22T12:08:56Z)
• AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection [23.91870504363899]
  Double-stream networks in multispectral detection employ two separate feature extraction branches for multi-modal data. This has hindered the widespread employment of multispectral pedestrian detection in embedded devices for autonomous systems. We introduce the Adaptive Modal Fusion Distillation (AMFD) framework, which can fully utilize the original modal features of the teacher network.
  arXiv  Detail & Related papers  (2024-05-21T17:17:17Z)
• CANAMRF: An Attention-Based Model for Multimodal Depression Detection [7.266707571724883]
  We present a Cross-modal Attention Network with Adaptive Multi-modal Recurrent Fusion (CANAMRF) for multimodal depression detection. CANAMRF is constructed by a multimodal feature extractor, an Adaptive Multimodal Recurrent Fusion module, and a Hybrid Attention Module.
  arXiv  Detail & Related papers  (2024-01-04T12:08:16Z)
• Cross-Attention is Not Enough: Incongruity-Aware Dynamic Hierarchical Fusion for Multimodal Affect Recognition [69.32305810128994]
  Incongruity between modalities poses a challenge for multimodal fusion, especially in affect recognition. We propose the Hierarchical Crossmodal Transformer with Dynamic Modality Gating (HCT-DMG), a lightweight incongruity-aware model. HCT-DMG: 1) outperforms previous multimodal models with a reduced size of approximately 0.8M parameters; 2) recognizes hard samples where incongruity makes affect recognition difficult; 3) mitigates the incongruity at the latent level in crossmodal attention.
  arXiv  Detail & Related papers  (2023-05-23T01:24:15Z)
• Distilled Mid-Fusion Transformer Networks for Multi-Modal Human Activity Recognition [34.424960016807795]
  Multi-modal Human Activity Recognition could utilize the complementary information to build models that can generalize well. Deep learning methods have shown promising results, their potential in extracting salient multi-modal spatial-temporal features has not been fully explored. A knowledge distillation-based Multi-modal Mid-Fusion approach, DMFT, is proposed to conduct informative feature extraction and fusion to resolve the Multi-modal Human Activity Recognition task efficiently.
  arXiv  Detail & Related papers  (2023-05-05T19:26:06Z)
• Decoupled Multimodal Distilling for Emotion Recognition [21.685394946415993]
  We propose a decoupled multimodal distillation (DMD) approach that facilitates flexible and adaptive crossmodal knowledge distillation. The representation of each modality is decoupled into two parts, i.e., modality-irrelevant/-exclusive spaces, in a self-regression manner. Experimental results show DMD consistently obtains superior performance than state-of-the-art MER methods.
  arXiv  Detail & Related papers  (2023-03-24T04:54:44Z)
• Multimodal Industrial Anomaly Detection via Hybrid Fusion [59.16333340582885]
  We propose a novel multimodal anomaly detection method with hybrid fusion scheme. Our model outperforms the state-of-the-art (SOTA) methods on both detection and segmentation precision on MVTecD-3 AD dataset.
  arXiv  Detail & Related papers  (2023-03-01T15:48:27Z)
• Multimodal Channel-Mixing: Channel and Spatial Masked AutoEncoder on Facial Action Unit Detection [12.509298933267225]
  This paper presents a novel multi-modal reconstruction network, named Multimodal Channel-Mixing (MCM) as a pre-trained model to learn robust representation for facilitating multi-modal fusion. The approach follows an early fusion setup, integrating a Channel-Mixing module, where two out of five channels are randomly dropped. This module not only reduces channel redundancy, but also facilitates multi-modal learning and reconstruction capabilities, resulting in robust feature learning.
  arXiv  Detail & Related papers  (2022-09-25T15:18:56Z)
• CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation [130.08432609780374]
  In 3D action recognition, there exists rich complementary information between skeleton modalities. We propose a new Cross-modal Mutual Distillation (CMD) framework with the following designs. Our approach outperforms existing self-supervised methods and sets a series of new records.
  arXiv  Detail & Related papers  (2022-08-26T06:06:09Z)
• Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction [125.18248926508045]
  We propose Channel-Exchanging-Network (CEN) which is self-adaptive, parameter-free, and more importantly, applicable for both multimodal fusion and multitask learning. CEN dynamically exchanges channels betweenworks of different modalities. For the application of dense image prediction, the validity of CEN is tested by four different scenarios.
  arXiv  Detail & Related papers  (2021-12-04T05:47:54Z)
• Unpaired Multi-modal Segmentation via Knowledge Distillation [77.39798870702174]
  We propose a novel learning scheme for unpaired cross-modality image segmentation. In our method, we heavily reuse network parameters, by sharing all convolutional kernels across CT and MRI. We have extensively validated our approach on two multi-class segmentation problems.
  arXiv  Detail & Related papers  (2020-01-06T20:03:17Z)

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.