Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Test-time AdaptationSimilar Papers 제목 키워드 기반
Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer
Automated segmentation of large volumes of medical images is often plagued by the limited availability of fully annotated data and the diversity of organ surface properties resulting from the use of different acquisition…
DiversityFew-Shot LearningImage SegmentationMedical Image Segmentation+2HMSN: Hyperbolic Self-Supervised Learning by Clustering with Ideal Prototypes
Hyperbolic manifolds for visual representation learning allow for effective learning of semantic class hierarchies by naturally embedding tree-like structures with low distortion within a low-dimensional representation s…
ClusteringFew-Shot LearningLinear evaluationRepresentation Learning+1Deep Image Prototype Learning with Geometric Heat-Kernel Priors
Learning unsupervised representations of medical imaging cohorts can reveal anatomically meaningful prototypes without expert labels, which are often noisy and fail to capture true pathological heterogeneity. However, ex…
Self-Attention Dense Depth Estimation Network for Unrectified Video Sequences
The dense depth estimation of a 3D scene has numerous applications, mainly in robotics and surveillance. LiDAR and radar sensors are the hardware solution for real-time depth estimation, but these sensors produce sparse …
Depth EstimationRectified-CFG++ for Flow Based Models
Classifier-free guidance (CFG) is the workhorse for steering large diffusion models toward text-conditioned targets, yet its native application to rectified flow (RF) based models provokes severe off-manifold drift, yiel…