Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics

• URL: http://arxiv.org/abs/2603.24057v1
• Date: Wed, 25 Mar 2026 08:03:30 GMT
• Title: Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics
• Abstract summary: We identify a failure mode termed Optimization Collapse, where detectors degenerate to random guessing on non-semantic forgeries.<n>We propose a Contrastive Regional Injection Transformer (CoRIT) which integrates a computationally efficient Contrastive Gradient Proxy (CGP) with three training-free strategies.<n>CoRIT mitigates optimization collapse and achieves state-of-the-art generalization across cross-domain and universal forgery benchmarks.
• Score: 12.973951916863989
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While Vision-Language Models (VLMs) like CLIP have emerged as a dominant paradigm for generalizable deepfake detection, a representational disconnect remains: their semantic-centric pre-training is ill-suited for capturing non-semantic artifacts inherent to hyper-realistic synthesis. In this work, we identify a failure mode termed Optimization Collapse, where detectors trained with Sharpness-Aware Minimization (SAM) degenerate to random guessing on non-semantic forgeries once the perturbation radius exceeds a narrow threshold. To theoretically formalize this collapse, we propose the Critical Optimization Radius (COR) to quantify the geometric stability of the optimization landscape, and leverage the Gradient Signal-to-Noise Ratio (GSNR) to measure generalization potential. We establish a theorem proving that COR increases monotonically with GSNR, thereby revealing that the geometric instability of SAM optimization originates from degraded intrinsic generalization potential. This result identifies the layer-wise attenuation of GSNR as the root cause of Optimization Collapse in detecting non-semantic forgeries. Although naively reducing perturbation radius yields stable convergence under SAM, it merely treats the symptom without mitigating the intrinsic generalization degradation, necessitating enhanced gradient fidelity. Building on this insight, we propose the Contrastive Regional Injection Transformer (CoRIT), which integrates a computationally efficient Contrastive Gradient Proxy (CGP) with three training-free strategies: Region Refinement Mask to suppress CGP variance, Regional Signal Injection to preserve CGP magnitude, and Hierarchical Representation Integration to attain more generalizable representations. Extensive experiments demonstrate that CoRIT mitigates optimization collapse and achieves state-of-the-art generalization across cross-domain and universal forgery benchmarks.

Related papers

• Across the Loss Landscape with Progressive Growth [51.366966420881646]
  We show how grow-and-optimize strategies to train toward flatter regions by viewing growth as progressive relaxation.<n>We empirically validate these predictions in controlled toy basins and in a realistic ResNet/CI-100 setting.<n>Although progressive subspace growth reliably produces flatter solutions, curvature reductions do not universally translate into improved test performance, highlighting subtleties in the flatness-generalization connection.
  arXiv  Detail & Related papers  (2026-08-25T13:50:48Z)
• 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)
• Heteroskedastic Signals in Budgeted LLM Verification: Structural Heterogeneity Limits Optimization Gains [4.560961083890857]
  Large language model (LLM) systems increasingly use uncertainty signals to allocate limited computation across verification, test-time scaling, tool execution, and other selective-compute decisions.<n>We show that uncertainty quality is heteroskedastic across cost strata, with some regions exhibiting near-random discriminability despite concentrating many errors.
  arXiv  Detail & Related papers  (2026-06-14T14:45:57Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• From Mean-Field Limits to Semiclassical Concentration: Global Convergence of the Canonical Evolutionary Strategy [0.602842844173992]
  We analyze global convergence in evolutionary algorithms via the semiclassical limit of a Schrdinger-type replicator-mutator equation.<n>We provide a rigorous hierarchy from a discrete individual-based dynamics to a deterministic mean-field limit.<n>Unlike consensus-driven methods that are prone to premature variance collapse when the global minimizer resides outside the initial support, the replicator-mutator dynamics of CES facilitate intrinsic mass transport.
  arXiv  Detail & Related papers  (2026-05-19T08:25:21Z)
• Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder [34.73963627819185]
  High-resolution (HR) joint optical and synthetic aperture radar (SAR) pretraining seeks modality synergy to mutually enhance single-source representations.<n>We propose CoDe-MAE, pioneering a textitbetter synergy with less alignment philosophy.<n>CoDe-MAE successfully prevents representation degradation and establishes new state-of-the-art performance across diverse single- and bi-modal downstream tasks.
  arXiv  Detail & Related papers  (2026-04-18T10:23:00Z)
• Taming the Instability: A Robust Second-Order Optimizer for Federated Learning over Non-IID Data [77.19117648492104]
  We present Federated Robust Curvature Optimization (FedRCO), a novel second-order optimization framework designed to improve convergence speed and reduce communication cost.<n>FedRCO addresses these challenges by integrating an efficient approximate curvature with a provable stability mechanism.<n>We show that FedRCO achieves superior robustness against diverse non-IID scenarios while achieving higher accuracy and faster convergence than both state-of-the-art first-order and second-order methods.
  arXiv  Detail & Related papers  (2026-03-30T11:37:46Z)
• 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)
• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers [9.020853139493239]
  We argue that one cause for non-convergence and instability is their non-decaying step-size scheduling.<n>We propose a series of new attack algorithms that enforce Monotonically Decreasing Coordinate-wise Step-sizes within sign-based adversarials.
  arXiv  Detail & Related papers  (2026-02-22T08:37:06Z)
• GTS: Inference-Time Scaling of Latent Reasoning with a Learnable Gaussian Thought Sampler [54.10960908347221]
  We model latent thought exploration as conditional sampling from learnable densities and instantiate this idea as a Gaussian Thought Sampler (GTS)<n>GTS predicts context-dependent perturbation distributions over continuous reasoning states and is trained with GRPO-style policy optimization while keeping the backbone frozen.
  arXiv  Detail & Related papers  (2026-02-15T09:57:47Z)
• Majorization-Minimization Networks for Inverse Problems: An Application to EEG Imaging [4.063392865490957]
  Inverse problems are often ill-posed and require optimization schemes with strong stability and convergence guarantees.<n>We propose a learned Majorization-Minimization (MM) framework for inverse problems within a bilevel optimization setting.<n>We learn a structured curvature majorant that governs each MM step while preserving classical MM descent guarantees.
  arXiv  Detail & Related papers  (2026-01-23T10:33:45Z)
• From Tail Universality to Bernstein-von Mises: A Unified Statistical Theory of Semi-Implicit Variational Inference [0.12183405753834557]
  Semi-implicit variational inference (SIVI) constructs approximate posteriors of the form $q() = int k(| z) r(dz)$<n>This paper develops a unified "approximation-optimization-statistics'' theory for such families.
  arXiv  Detail & Related papers  (2025-12-05T19:26:25Z)
• Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling [82.52485740425321]
  Adrial attacks present a critical challenge to deep neural networks' robustness.<n> transferability of adversarial attacks faces a dilemma between Exploitation (maximizing attack potency) and Exploration (enhancing cross-model generalization)
  arXiv  Detail & Related papers  (2025-11-01T05:43:47Z)
• Convergence and Generalization of Anti-Regularization for Parametric Models [0.0]
  Anti-regularization introduces a reward term with a reversed sign into the loss function.<n>We formalize spectral safety conditions and trust-region constraints.<n>We design a lightweight safeguard that combines a projection operator with gradient clipping to guarantee stable intervention.
  arXiv  Detail & Related papers  (2025-08-24T15:34:17Z)
• ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model [51.83639270669481]
  Unsupervised anomaly detection in hyperspectral images (HSI) aims to detect unknown targets from backgrounds.<n>HSI studies are hindered by steep computational costs due to the high-dimensional property of HSI and dense sampling-based training paradigm.<n>We propose an Asymmetrical Consensus State Space Model (ACMamba) to significantly reduce computational costs without compromising accuracy.
  arXiv  Detail & Related papers  (2025-04-16T05:33:42Z)
• Gradient Normalization Provably Benefits Nonconvex SGD under Heavy-Tailed Noise [60.92029979853314]
  We investigate the roles of gradient normalization and clipping in ensuring the convergence of Gradient Descent (SGD) under heavy-tailed noise. Our work provides the first theoretical evidence demonstrating the benefits of gradient normalization in SGD under heavy-tailed noise. We introduce an accelerated SGD variant incorporating gradient normalization and clipping, further enhancing convergence rates under heavy-tailed noise.
  arXiv  Detail & Related papers  (2024-10-21T22:40:42Z)

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.