MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement

• URL: http://arxiv.org/abs/2605.16081v1
• Date: Fri, 15 May 2026 15:44:19 GMT
• Title: MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement
• Abstract summary: Model-induced label noise dominates noise in classical robust learning.<n>We propose Model-Induced Noise Decoupling (MIND), a theoretically grounded framework addressing this dilemma.<n>MIND significantly outperforms state-of-the-art methods on complex benchmarks.
• Score: 3.626013617212667
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The paradigm of learning from automatic annotations driven by pre-trained experts and Foundation Models dominates data-hungry applications. However, it introduces a critical challenge: model-induced label noise. Unlike stochastic noise in classical robust learning, this noise stems from annotator inductive biases, manifesting as systematic errors tightly coupled with local feature manifolds. Existing methods relying on global transition matrices underfit these structural patterns, while learning instance-specific matrices remains mathematically intractable. We propose Model-Induced Noise Decoupling (MIND), a theoretically grounded framework addressing this dilemma. We demonstrate that the high-dimensional noise manifold can be decoupled into tractable, subspace-dependent components via Latent Manifold Disentanglement. Specifically, our Latent Decoupling Estimator (LDE) dynamically projects samples into latent structural clusters with consistent error modes, facilitating noise identifiability without ground-truth anchor points. To rigorously evaluate robustness, we adopt a hierarchical protocol: moving from controlled noise on CIFAR-100 to a structural stress test on large-scale real-world 3D datasets (S3DIS, ScanNet), where error patterns explicitly couple with geometric manifolds. Empirically, MIND significantly outperforms state-of-the-art methods on these complex benchmarks and effectively corrects zero-shot hallucinations from Vision-Language Models (e.g., OpenSeg), highlighting its potential as a robust distillation framework for Foundation Models.

Related papers

• Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection [58.25418970608328]
  We study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains.<n>Existing methods mainly rely on simulation-driven strategies, such as data augmentation or textual prompts, to enlarge the training distribution.<n>We propose Manifold Regression with Visual-Text Dual Chain-of-Thought (MR-DCoT), which formulates unknown-domain generalization as a manifold regression problem.
  arXiv  Detail & Related papers  (2026-07-08T09:27:15Z)
• RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval [24.383054290279173]
  RankVR is a framework designed to construct a robust Composed Image Retrieval model via global structure consistency and dynamic value perception.<n>It significantly outperforms existing state-of-the-art methods, validating its superior robustness in noisy environments.
  arXiv  Detail & Related papers  (2026-06-10T06:06:34Z)
• CANMOT: Class-Aware Noise Modeling for Multi-Object Tracking in Autonomous Driving [1.2744523252873352]
  CANMOT is a class-aware and object-aligned noise modeling framework for KF-based 3D MOT.<n>Experiments show that class-aware and object-aligned noise modeling improves tracking performance and substantially reduces identity.<n>Results reveal severe overconfidence in standard KF-based MOT baselines.
  arXiv  Detail & Related papers  (2026-06-02T12:56:31Z)
• GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels [7.09131557837911]
  Deep neural networks (DNNs) experience significant performance degradation when processing noisy labels.<n>Current mainstream approaches attempt to mitigate this issue by passively filtering clean samples during training.<n>We highlight for the first time the fundamental importance of actively reshaping feature space geometry for learning from noisy data.
  arXiv  Detail & Related papers  (2026-05-20T05:24:43Z)
• Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine [60.669081685261965]
  Diffusion models generate high-dimensional data with remarkable quality.<n>How their training efficiently learns the score function remains theoretically unexplained.<n>We instantiate this principle as Score-induced Latent Diffusion (SiLD)
  arXiv  Detail & Related papers  (2026-05-16T16:51:10Z)
• Provable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs [77.42033827176806]
  One-Shot Federated Learning, where a central server learns a global model in a single communication round, has emerged as a promising paradigm.<n>We propose a novel Federated Model Inversion and Token Relabel framework, which trains the global model by fully exploiting all patches of synthetic images.
  arXiv  Detail & Related papers  (2026-05-11T15:49:08Z)
• One CT Unified Model Training Framework to Rule All Scanning Protocols [32.68329101435685]
  Non-ideal measurement computed tomography (NICT) is expanding the clinical use of CT.<n>Most methods require paired data, which is an impractical demand due to inevitable organ motion.<n>We propose an Uncertainty-Guided Manifold Smoothing (UMS) framework to bridge the gaps between sub-manifolds.
  arXiv  Detail & Related papers  (2026-03-16T09:26:32Z)
• Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision [11.159231524113764]
  Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs)<n>In this paper, we propose the textbfGuided Verifier framework to address these structural limitations.<n>We develop a specialized data synthesis pipeline targeting multimodal hallucinations, constructing textbfCoRe dataset of process-level negatives and textbfCorrect-guide textbfReasoning trajectories to train the guided verifier.
  arXiv  Detail & Related papers  (2026-02-04T07:38:42Z)
• Noise-Robust Tiny Object Localization with Flows [63.60972031108944]
  We propose a noise-robust localization framework leveraging normalizing flows for flexible error modeling and uncertainty-guided optimization.<n>Our method captures complex, non-Gaussian prediction distributions through flow-based error modeling, enabling robust learning under noisy supervision.<n>An uncertainty-aware gradient modulation mechanism further suppresses learning from high-uncertainty, noise-prone samples, mitigating overfitting while stabilizing training.
  arXiv  Detail & Related papers  (2026-01-02T09:16:55Z)
• Towards Robust Image Denoising with Scale Equivariance [10.894808298340994]
  We argue that incorporating scale-equivariant structures enables models to better adapt from training on spatially uniform noise to inference on spatially non-uniform degradations.<n>We propose a robust blind denoising framework equipped with two key components: a Heterogeneous Normalization Module (HNM) and an Interactive Gating Module (IGM)
  arXiv  Detail & Related papers  (2025-08-05T00:06:28Z)
• Robust Learning under Hybrid Noise [24.36707245704713]
  We propose a novel unified learning framework called "Feature and Label Recovery" (FLR) to combat the hybrid noise from the perspective of data recovery.
  arXiv  Detail & Related papers  (2024-07-04T16:13:25Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• Latent Class-Conditional Noise Model [54.56899309997246]
  We introduce a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples.
  arXiv  Detail & Related papers  (2023-02-19T15:24:37Z)

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.