Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift

• URL: http://arxiv.org/abs/2608.15037v1
• Date: Sat, 15 Aug 2026 04:42:14 GMT
• Title: Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift
• Abstract summary: We introduce PRISM, a training-free, source-free Test-Time Adaptation (TTA) framework grounded in the Affine Noise Hypothesis.<n>At inference, adaptation reduces to one matrix-vector multiplication in 0.0009 ms, making it substantially faster than gradient-based TTA.<n>On UrbanSound8K, PRISM improves over the zero-shot baseline by 12.94 percentage points and surpasses an oracle-assisted TTA baseline by 9.41 percentage points.
• Score: 3.704942101286518
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA), which reinforces noise rather than signal, or on prompt tuning that requires privileged noise annotations unavailable at inference. We address these failures with PRISM (Prototype-Rectified Iterative Self-supervised Manifold Denoising), a training-free, source-free TTA framework grounded in the Affine Noise Hypothesis: severe acoustic noise induces a low-rank affine shift in the multimodal latent space, with more than 90% of distortion energy confined to the leading 60 principal components. PRISM estimates and reverses this distortion from an unlabeled target batch using frozen text prototypes as geometric anchors via three closed-form geometric corrections compiled into a single static projection matrix by Affine Bias Regression. At inference, adaptation reduces to one matrix-vector multiplication in 0.0009 ms, making it substantially faster than gradient-based TTA while requiring no additional training. On UrbanSound8K, PRISM improves over the zero-shot baseline by 12.94 percentage points and surpasses an oracle-assisted TTA baseline by 9.41 percentage points, despite never observing its privileged augmented noise prompts. We further identify the Polyphonic Trap, a principled failure mode of subspace deflation for broadband classes, and resolve it via Confidence-Aware Regression (CAR), recovering up to 8.16 percentage points for the worst-affected class.

Related papers

• The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP [6.450516062706025]
  In joint-embedding architectures such as CLIP this introduces a failure mode distinct from quantized CNN classifiers.<n>We characterize this as Quantization-Induced Representation Collapse (QIRC) and quantify it on INT8 replacing CLIP ViT-B/32.<n>We propose LRA-EE (Layer-wise Representation-Aware Early Exit), which bypasses noise-saturated deep layers.<n>On ImageNet-1K zero-shot classification, LRA-EE reduces FLOPs by 13.4% and improves Top-1 accuracy by +2.44%p (58.72% -> 61.16%) over the INT8 baseline
  arXiv  Detail & Related papers  (2026-05-26T00:45:46Z)
• Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models [52.18157855348584]
  Test-Time Adaptation (TTA) via entropy minimization (EM) has proven effective for classification tasks, yet its application remains theoretically fragmented.<n>In this work, we deriving a rigorous formulation of EM tailored to autoregressive models.<n>We show that the exact objective naturally decomposes into a token-level policy gradient loss and a token-level entropy loss, and we reinterpret prior methods as partial realizations of this unified formulation.<n>Using Whisper ASR as a testbed, we demonstrate that our approach consistently improves performance across more than 20 diverse domains, including acoustic noise, accents, and multilingual settings.
  arXiv  Detail & Related papers  (2026-05-05T12:00:06Z)
• Intrinsic Gradient Suppression for Label-Noise Prompt Tuning in Vision-Language Models [26.29904418630642]
  We show that DSPT induces a self-adaptive saturation zone that suppresses gradients from high-error noisy samples.<n>Extensive experiments confirm that this simple, drop-in design achieves state-of-the-art robustness across various noisy benchmarks.
  arXiv  Detail & Related papers  (2026-05-01T11:57:51Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• Variational Rectification Inference for Learning with Noisy Labels [74.85528327499662]
  We propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions.<n>VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable.<n>By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function.
  arXiv  Detail & Related papers  (2026-03-18T01:25:08Z)
• The Malignant Tail: Spectral Segregation of Label Noise in Over-Parameterized Networks [0.0]
  We experimentally isolate the Malignant Tail, a failure mode where networks functionally segregate signal and noise.<n>We show that untrained networks actively segregate noise, allowing post-hoc Explicit Spectral Truncation to surgically prune the noise-dominated subspace.<n>Our findings suggest that under label noise, excess spectral capacity is not harmless redundancy but a latent structural liability.
  arXiv  Detail & Related papers  (2026-03-02T16:39:42Z)
• Noise-Adaptive Regularization for Robust Multi-Label Remote Sensing Image Classification [5.658568324275769]
  We propose NAR, a noise-adaptive regularization method that distinguishes between additive and subtractive noise.<n> NAR consistently improves robustness compared with existing methods.<n>Performance improvements are most pronounced under subtractive and mixed noise.
  arXiv  Detail & Related papers  (2026-01-13T11:16:45Z)
• Test-time Adaptive Hierarchical Co-enhanced Denoising Network for Reliable Multimodal Classification [55.56234913868664]
  We propose Test-time Adaptive Hierarchical Co-enhanced Denoising Network (TAHCD) for reliable learning on multimodal data.<n>The proposed method achieves superior classification performance, robustness, and generalization compared with state-of-the-art reliable multimodal learning approaches.
  arXiv  Detail & Related papers  (2026-01-12T03:14:12Z)
• Pay Attention Later: From Vector Space Diffusion to Linearithmic Spectral Phase-Locking [0.0]
  Standard Transformers suffer from a "Semantic Alignment Tax"<n>We introduce the Phase-Resonant Intelligent Spectral Model (PRISM)<n>PRISM encodes semantic identity as resonant frequencies in the complex domain (Cd) and replaces quadratic self-attention with linearithmic O(N log N) Gated Harmonic Convolutions.
  arXiv  Detail & Related papers  (2025-12-01T02:46:15Z)
• ROPO: Robust Preference Optimization for Large Language Models [59.10763211091664]
  We propose an iterative alignment approach that integrates noise-tolerance and filtering of noisy samples without the aid of external models. Experiments on three widely-used datasets with Mistral-7B and Llama-2-7B demonstrate that ROPO significantly outperforms existing preference alignment methods.
  arXiv  Detail & Related papers  (2024-04-05T13:58:51Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• 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.