FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning

• URL: http://arxiv.org/abs/2511.20997v1
• Date: Wed, 26 Nov 2025 02:50:29 GMT
• Title: FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning
• Authors: Jiaoyang Li, Jun Fang, Tianhao Gao, Xiaohui Zhang, Zhiyuan Liu, Chao Liu, Pengzhang Liu, Qixia Jiang,
• Abstract summary: We study the role of noise gradient in representation learning from both-based and feature distribution perspectives.<n>We propose FANoise, a novel feature-adaptive noise injection strategy.<n>Under this framework, experiments demonstrate that FANoise consistently improves overall performance on multimodal tasks.
• Score: 24.94576263410761
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Representation learning is fundamental to modern machine learning, powering applications such as text retrieval and multimodal understanding. However, learning robust and generalizable representations remains challenging. While prior work has demonstrated that active noise injection, a form of data augmentation, can enhance encoding performance, most existing methods rely on heuristic or static noise, overlooking the dynamic nature of feature distributions during training. In this work, we systematically study the role of noise in representation learning from both gradient-based and feature distribution perspectives, using InfoNCE loss as a representative example. Focusing on multimodal representation learning, we propose FANoise, a novel feature-adaptive noise injection strategy. By leveraging the dynamics of contrastive learning, FANoise effectively mitigates the negative impacts of noise while preserving its benefits. Under this theoretically grounded framework, comprehensive experiments demonstrate that FANoise consistently improves overall performance on multimodal tasks across various base VLM models.

Related papers

• Multi-View Learning with Context-Guided Receptance for Image Denoising [18.175992709188026]
  Image denoising is essential in low-level vision applications such as photography and automated driving.<n>Existing methods struggle with distinguishing complex noise patterns in real-world scenes and consume significant computational resources.<n>In this work, a Context-guided Receptance Weighted Key-Value (M) model is proposed, combining enhanced multi-view feature integration with efficient sequence modeling.<n>The model is validated on multiple real-world image denoising datasets, outperforming the existing state-of-the-art methods quantitatively and reducing inference time up to 40%.
  arXiv  Detail & Related papers  (2025-05-05T14:57:43Z)
• Underlying Semantic Diffusion for Effective and Efficient In-Context Learning [113.4003355229632]
  Underlying Semantic Diffusion (US-Diffusion) is an enhanced diffusion model that boosts underlying semantics learning, computational efficiency, and in-context learning capabilities.<n>We present a Feedback-Aided Learning (FAL) framework, which leverages feedback signals to guide the model in capturing semantic details.<n>We also propose a plug-and-play Efficient Sampling Strategy (ESS) for dense sampling at time steps with high-noise levels.
  arXiv  Detail & Related papers  (2025-03-06T03:06:22Z)
• Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning [24.671771440617288]
  We propose a new Robust Disentangled Counterfactual Learning (RDCL) approach for physical audiovisual commonsense reasoning.<n>The main challenge is how to imitate the reasoning ability of humans, even under the scenario of missing modalities.<n>Our proposed method is a plug-and-play module that can be incorporated into any baseline including VLMs.
  arXiv  Detail & Related papers  (2025-02-18T01:49:45Z)
• Enhance Vision-Language Alignment with Noise [59.2608298578913]
  We investigate whether the frozen model can be fine-tuned by customized noise.<n>We propose Positive-incentive Noise (PiNI) which can fine-tune CLIP via injecting noise into both visual and text encoders.
  arXiv  Detail & Related papers  (2024-12-14T12:58:15Z)
• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)
• Policy Gradient-Driven Noise Mask [3.69758875412828]
  We propose a novel pretraining pipeline that learns to generate conditional noise masks specifically tailored to improve performance on multi-modal and multi-organ datasets.<n>A key aspect is that the policy network's role is limited to obtaining an intermediate (or heated) model before fine-tuning.<n>Results demonstrate that fine-tuning the intermediate models consistently outperforms conventional training algorithms on both classification and generalization to unseen concept tasks.
  arXiv  Detail & Related papers  (2024-04-29T23:53:42Z)
• NoisyNN: Exploring the Impact of Information Entropy Change in Learning Systems [15.068228411480957]
  We show that specific noise can boost the performance of various deep models under certain conditions.<n>We categorize the noise into two types, positive noise (PN) and harmful noise (HN), based on whether the noise can help reduce the task complexity.
  arXiv  Detail & Related papers  (2023-09-19T14:04:04Z)
• Deep Active Learning with Noise Stability [24.54974925491753]
  Uncertainty estimation for unlabeled data is crucial to active learning. We propose a novel algorithm that leverages noise stability to estimate data uncertainty. Our method is generally applicable in various tasks, including computer vision, natural language processing, and structural data analysis.
  arXiv  Detail & Related papers  (2022-05-26T13:21:01Z)
• Visual Adversarial Imitation Learning using Variational Models [60.69745540036375]
  Reward function specification remains a major impediment for learning behaviors through deep reinforcement learning. Visual demonstrations of desired behaviors often presents an easier and more natural way to teach agents. We develop a variational model-based adversarial imitation learning algorithm.
  arXiv  Detail & Related papers  (2021-07-16T00:15:18Z)
• 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)
• Learning to Learn Kernels with Variational Random Features [118.09565227041844]
  We introduce kernels with random Fourier features in the meta-learning framework to leverage their strong few-shot learning ability. We formulate the optimization of MetaVRF as a variational inference problem. We show that MetaVRF delivers much better, or at least competitive, performance compared to existing meta-learning alternatives.
  arXiv  Detail & Related papers  (2020-06-11T18:05:29Z)

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.