Mind the Gap: Learning Modality-Agnostic Representations with a Cross-Modality UNet

• URL: http://arxiv.org/abs/2605.16887v1
• Date: Sat, 16 May 2026 09:00:54 GMT
• Title: Mind the Gap: Learning Modality-Agnostic Representations with a Cross-Modality UNet
• Abstract summary: Cross-modality recognition has many important applications in science, law enforcement and entertainment.<n>We propose a compact encoder-decoder neural module (cmUNet) to learn modality-agnostic representations while retaining identity-related information.<n>For cross-modality matching, we propose MarrNet where cmUNet is connected to a standard feature extraction network which takes as inputs the modality-agnostic representations and outputs similarity scores for matching.
• Score: 21.513499794627165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-modality recognition has many important applications in science, law enforcement and entertainment. Popular methods to bridge the modality gap include reducing the distributional differences of representations of different modalities, learning indistinguishable representations or explicit modality transfer. The first two approaches suffer from the loss of discriminant information while removing the modality-specific variations. The third one heavily relies on the successful modality transfer, could face catastrophic performance drop when explicit modality transfers are not possible or difficult. To tackle this problem, we proposed a compact encoder-decoder neural module (cmUNet) to learn modality-agnostic representations while retaining identity-related information. This is achieved through cross-modality transformation and in-modality reconstruction, enhanced by an adversarial/perceptual loss which encourages indistinguishability of representations in the original sample space. For cross-modality matching, we propose MarrNet where cmUNet is connected to a standard feature extraction network which takes as inputs the modality-agnostic representations and outputs similarity scores for matching. We validated our method on five challenging tasks, namely Raman-infrared spectrum matching, cross-modality person re-identification and heterogeneous (photo-sketch, visible-near infrared and visible-thermal) face recognition, where MarrNet showed superior performance compared to state-of-the-art methods. Furthermore, it is observed that a cross-modality matching method could be biased to extract discriminant information from partial or even wrong regions, due to incompetence of dealing with modality gaps, which subsequently leads to poor generalization. We show that robustness to occlusions can be an indicator of whether a method can well bridge the modality gap.

Related papers

• Modality-Aware Bias Mitigation and Invariance Learning for Unsupervised Visible-Infrared Person Re-Identification [14.343677160918723]
  Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match individuals across visible and infrared cameras without relying on any annotation.<n> estimating reliable cross-modality association is a major challenge in USVI-ReID.<n>This paper focuses on addressing cross-modality learning from two aspects: bias-mitigated global association and modality-invariant representation learning.
  arXiv  Detail & Related papers  (2025-12-08T17:42:28Z)
• Cross-Modality Perturbation Synergy Attack for Person Re-identification [66.48494594909123]
  Cross-modality person re-identification (ReID) systems are based on RGB images.<n>Main challenge in cross-modality ReID lies in effectively dealing with visual differences between different modalities.<n>Existing attack methods have primarily focused on the characteristics of the visible image modality.<n>This study proposes a universal perturbation attack specifically designed for cross-modality ReID.
  arXiv  Detail & Related papers  (2024-01-18T15:56:23Z)
• Modality Unifying Network for Visible-Infrared Person Re-Identification [24.186989535051623]
  Visible-infrared person re-identification (VI-ReID) is a challenging task due to large cross-modality discrepancies and intra-class variations. Existing methods mainly focus on learning modality-shared representations by embedding different modalities into the same feature space. We propose a novel Modality Unifying Network (MUN) to explore a robust auxiliary modality for VI-ReID.
  arXiv  Detail & Related papers  (2023-09-12T14:22:22Z)
• 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)
• Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing [73.29587731448345]
  We propose a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH) We learn informative representations that can preserve both intra- and inter-modal similarities. The proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods.
  arXiv  Detail & Related papers  (2021-12-13T08:58:03Z)
• Heterogeneous Visible-Thermal and Visible-Infrared Face Recognition using Unit-Class Loss and Cross-Modality Discriminator [0.43748379918040853]
  We propose an end-to-end framework for cross-modal face recognition. A novel Unit-Class Loss is proposed for preserving identity information while discarding modality information. The proposed network can be used to extract modality-independent vector representations or a matching-pair classification for test images.
  arXiv  Detail & Related papers  (2021-11-29T06:14:00Z)
• CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification [38.96033760300123]
  Cross-modality transformer-based method (CMTR) for visible-infrared person re-identification task. We design the novel modality embeddings, which are fused with token embeddings to encode modalities' information. Our proposed CMTR model's performance significantly surpasses existing outstanding CNN-based methods.
  arXiv  Detail & Related papers  (2021-10-18T03:12:59Z)
• Exploring Modality-shared Appearance Features and Modality-invariant Relation Features for Cross-modality Person Re-Identification [72.95858515157603]
  Cross-modality person re-identification works rely on discriminative modality-shared features. Despite some initial success, such modality-shared appearance features cannot capture enough modality-invariant information. A novel cross-modality quadruplet loss is proposed to further reduce the cross-modality variations.
  arXiv  Detail & Related papers  (2021-04-23T11:14:07Z)
• Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification [208.1227090864602]
  Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Existing VI-ReID methods tend to learn global representations, which have limited discriminability and weak robustness to noisy images. We propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID.
  arXiv  Detail & Related papers  (2020-07-18T03:08:13Z)
• When Relation Networks meet GANs: Relation GANs with Triplet Loss [110.7572918636599]
  Training stability is still a lingering concern of generative adversarial networks (GANs) In this paper, we explore a relation network architecture for the discriminator and design a triplet loss which performs better generalization and stability. Experiments on benchmark datasets show that the proposed relation discriminator and new loss can provide significant improvement on variable vision tasks.
  arXiv  Detail & Related papers  (2020-02-24T11:35:28Z)

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.