Adjoint Inversion Reveals Holographic Superposition and Destructive Interference in CNN Classifiers

• URL: http://arxiv.org/abs/2604.27529v1
• Date: Thu, 30 Apr 2026 07:32:07 GMT
• Title: Adjoint Inversion Reveals Holographic Superposition and Destructive Interference in CNN Classifiers
• Abstract summary: We introduce a hallucination-free inversion framework built on magnitude-phase decoupling and Local Adjoint Correctors.<n>Our method mathematically guarantees that the spatial gradient support of every reconstruction stems strictly from genuinely active channels.<n>Using this framework as a geometric probe, we uncover the first pixel-level evidence of strong superposition in vision encoders.
• Score: 0.33842793760651557
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A foundational assumption in CNN interpretability -- that deep encoders suppress background pixels while classifiers merely select from a cleaned feature pool (the Spatial Funnel Hypothesis) -- remains untested due to spatial hallucinations in existing visualization tools. We address this by introducing a hallucination-free inversion framework built on magnitude-phase decoupling and Local Adjoint Correctors. Our method mathematically guarantees that the spatial gradient support of every reconstruction stems strictly from genuinely active channels. Using this framework as a geometric probe, we uncover the first pixel-level evidence of strong superposition in vision encoders. We show that per-channel inversions are uniformly holographic: positive and negative weight reconstructions are visually and energetically indistinguishable. However, their algebraic sum sharply concentrates on the foreground. This proves classification operates via destructive interference -- classifier weights cancel a shared background direction in pixel space and constructively assemble class-discriminative residuals, directly falsifying the Spatial Funnel Hypothesis. This interference model identifies the volume of the admissible interference subspace as the geometric quantity governing channel requirements. We prove this volume is dual to the GAP covariance determinant, yielding a covariance-volume channel selection algorithm with a $(1-1/e)$ approximation guarantee. This algorithm mathematically reveals out-of-distribution (OOD) failure as a measurable collapse of the covariance volume essential for interference-based classification. Our framework extends seamlessly to attention-based heads without retraining.

Related papers

• The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search [19.846305722187328]
  Retrieval-Augmented Generation (RAG) shifts toward diverse portfolio generation.<n>It is stymied by two critical bottlenecks: flawed measurement of evidence utilization, and suboptimal context budget allocation.<n>We introduce a causal leave-one-out probe that accurately isolates generative reliance.<n>We prove that the prevailing strategy of monolithic context widening is an architectural trap penalized by relevance decay.
  arXiv  Detail & Related papers  (2026-08-24T13:44:11Z)
• LoTA-N2N: Local Trace Adaptation for Zero-Shot Self-Supervised Image Denoising [43.31076762214249]
  Single-image self-supervised denoising replaces unavailable clean targets with surrogate targets constructed from noisy observations.<n>We propose LoTA-N2N, a two-stage zero-shot adaptation framework.<n>We show that the local construction prevents spatial cancellation and upper-bounds the magnitude of the corresponding global interaction.
  arXiv  Detail & Related papers  (2026-07-27T08:16:15Z)
• SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere [90.85001795656633]
  Video anomaly detection (VAD) aims to automatically identify events that deviate from normal patterns in untrimmed surveillance videos.<n>We propose SphereVAD, a fully training-free, zero-shot VAD framework that recasts anomaly discrimination as von Mises-Fisher (vMF) likelihood-ratio geodesic inference on the unit hypersphere.
  arXiv  Detail & Related papers  (2026-05-08T16:57:38Z)
• Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering [57.38215918201251]
  We propose HERL, a Hyperbolic Enhanced Representation Learning framework for Incomplete Multi-View Clustering.<n> operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning.<n>We show that HERL consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-18T10:50:46Z)
• DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting [80.43237927269575]
  In this paper, we revisit sparse-view 3DGS reconstruction from a new perspective.<n>We identify the core challenge as the unobservability of Gaussian primitive reliability.<n>Motivated by this observation, we propose a unified Dual-domain Observation and geometrics in rendered images framework.
  arXiv  Detail & Related papers  (2026-04-08T07:01:24Z)
• 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)
• MirrorLA: Reflecting Feature Map for Vision Linear Attention [49.41670925034762]
  Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance.<n>We propose MirrorLA, a geometric framework that substitutes passive truncation with active reorientation.<n>MirrorLA achieves state-of-the-art performance across standard benchmarks, demonstrating that strictly linear efficiency can be achieved without compromising representational fidelity.
  arXiv  Detail & Related papers  (2026-02-04T09:14:09Z)
• ARGUS: Adaptive Rotation-Invariant Geometric Unsupervised System [0.0]
  This paper introduces Argus, a framework that reconceptualizes drift detection as tracking local statistics over a fixed spatial partition of the data manifold.<n> Voronoi tessellations over canonical orthonormal frames yield drift metrics that are invariant to transformations.<n>A graph-theoretic characterization of drift propagation is developed that distinguishes coherent distributional shifts from isolated perturbations.
  arXiv  Detail & Related papers  (2026-01-03T22:39:20Z)
• Spatial regularisation for improved accuracy and interpretability in keypoint-based registration [5.286949071316761]
  Recent approaches based on unsupervised keypoint detection stand out as very promising for interpretability.<n>Here, we propose a three-fold loss to regularise the spatial distribution of the features.<n>Our loss considerably improves the interpretability of the features, which now correspond to precise and anatomically meaningful landmarks.
  arXiv  Detail & Related papers  (2025-03-06T14:48:25Z)
• Disentangled Interleaving Variational Encoding [1.132458063021286]
  We propose a principled approach to disentangle the original input into marginal and conditional probability distributions in the latent space of a variational autoencoder.<n>Our proposed model, Deep Disentangled Interleaving Variational.<n>coder (DeepDIVE), learns disentangled features from the original input to form clusters in the embedding space.<n>Experiments on two public datasets show that DeepDIVE disentangles the original input and yields forecast accuracies better than the original VAE.
  arXiv  Detail & Related papers  (2025-01-15T10:50:54Z)
• Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment [53.401889855278704]
  Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. We propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local to local (L2L) similarity metric. Experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2022-10-04T07:54:40Z)
• Dencentralized learning in the presence of low-rank noise [57.18977364494388]
  Observations collected by agents in a network may be unreliable due to observation noise or interference. This paper proposes a distributed algorithm that allows each node to improve the reliability of its own observation.
  arXiv  Detail & Related papers  (2022-03-18T09:13:57Z)
• Correlation Clustering Reconstruction in Semi-Adversarial Models [70.11015369368272]
  Correlation Clustering is an important clustering problem with many applications. We study the reconstruction version of this problem in which one is seeking to reconstruct a latent clustering corrupted by random noise and adversarial modifications.
  arXiv  Detail & Related papers  (2021-08-10T14:46:17Z)

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.