Edges Before Embeddings: A Confidence-Aware Blur Gate for Vision-Language Pipelines

• URL: http://arxiv.org/abs/2606.25838v1
• Date: Wed, 24 Jun 2026 13:51:42 GMT
• Title: Edges Before Embeddings: A Confidence-Aware Blur Gate for Vision-Language Pipelines
• Abstract summary: MagikaDocumentFromPixel classifies a single image as sharp, blurred, or uncertain in roughly 7 ms on a single CPU core.<n>A Laplacian-language auxiliary input channel gives the network direct access to the spectral evidence that classical blurs rely on.<n>The final recipe MobileNetV3-Large with the EPM trained at 384x384 on paired GoPro Large frames, evaluated with 5-scale test-time augmentation reaches F1 = 0.9803 (AUC 0.9989) with a 17 MB ONNX artifact.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Production vision pipelines silently degrade on blurry input, wasting compute on downstream OCR, retrieval, and vision-language model (VLM) calls that cannot recover a usable output. We present MagikaDocumentFromPixel, a lightweight, CPU-friendly image quality gate that classifies a single image as sharp, blurred, or uncertain in roughly 7 ms on a single CPU core. The contributions are (i) a recipe selected from a 46-configuration, 8-sweep empirical search that isolates input resolution as the dominant lever and shows architecture capacity only pays off at >= 384 px; (ii) a confidence-aware routing formalism grounded in classical selective prediction; (iii) the Edge Prior Module (EPM), a Laplacian-magnitude auxiliary input channel that gives the network direct access to the spectral evidence that classical blur heuristics rely on and that lifts test F1 by +1.3 points in a matched-env comparison; and (iv) an observation that the gate is one instance of a recurring design pattern that appears independently in Magika content-type detection, risk-controlled OCR with VLMs, and DocVLM. The final recipe MobileNetV3-Large with the EPM trained at 384x384 on paired GoPro Large frames, evaluated with 5-scale test-time augmentation reaches F1 = 0.9803 (AUC 0.9989) with a 17 MB ONNX artifact, improving over our fixed-scale baseline on the same hardware (F1 = 0.9672) by +1.31 points. We are explicit about limitations: results are on a single motion-blur distribution, numbers are from a single seed, and calibration is qualitative rather than measured.

Related papers

• Federated Binary Gating with Server-Side Vision-Language Inference for Surveillance Anomaly Classification [0.24629531282150874]
  We propose a hybrid two-stage architecture that combines a CNN gate with server-side zero-shot VLM inference.<n>We evaluate this design on UCF-Crime grouped into five coarse metaclasses and implement the federated stage in a real three-node heterogeneous deployment.
  arXiv  Detail & Related papers  (2026-09-07T12:14:57Z)
• Mind the Rift: Cross-Scale Coupling Mismatch for AI-Generated Video Detection [10.264738258468254]
  Cross-scale coupling mismatch is a new forensic signal.<n>In natural videos, macro-level temporal dynamics and micro-level residual patterns are intrinsically coupled by the unified imaging physics pipeline.<n>But AI generators, whose training objectives do not explicitly preserve this joint distribution, systematically violate this coupling.<n>Detecting such mismatch is challenging because it requires independently extracting information at both scales.
  arXiv  Detail & Related papers  (2026-09-01T05:23:48Z)
• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model [60.85752511708308]
  We present Mage-VL, an efficient streaming foundation model for real-time multimodal understanding and interaction.<n>At its core, our custom tokenizer, Mage-ViT, replaces uniform frame sampling by selectively encoding dynamic, entropy-rich regions.<n>We establish AI4AI data pipelines encompassing prompt-code joint optimization for captioning and AI-driven performance diagnosis.
  arXiv  Detail & Related papers  (2026-07-27T17:59:53Z)
• Multimodal Ambivalence and Hesitancy Recognition via Cross-Attention and Gated Fusion [1.6950215926321557]
  We present a framework for Ambivalence/Hesitancy (A/H) recognition in video, developed for the ABAW11 challenge at ECCV 2026.<n>The proposed approach fuses textual, acoustic, and visual modalities extracted from the BAH dataset.<n>This model achieves a Macro F1 of textbf0.7394 on the validation set, a relative improvement of 11.0% over the best unimodal baseline.
  arXiv  Detail & Related papers  (2026-07-17T09:23:36Z)
• Disagreement-Based Cross-Model Routing for Implicit Video Question Answering [0.0]
  We study multiple-choice video question answering on the ImplicitQA benchmark.<n>On this benchmark a single frontier video LLM already operates near its accuracy ceiling.<n>We propose disagreement-based cross-model routing, a pure inference-time procedure that requires no labels and no training.
  arXiv  Detail & Related papers  (2026-05-31T05:56:27Z)
• Detect Before You Leap: Mirage Detection in Vision-Language Models [2.6212127510234797]
  Vision-language models (VLMs) can produce confident visual answers even when the required visual evidence is missing, blank, or unrelated to the question.<n>We study pre-release mirage detection: given an image-question pair, the goal is to determine whether a VLM should answer or abstain.<n>We propose Text-Conditioned Layer-wise Internal Alignment (TC-LIA), a model-agnostic method that probes patch-token representations across the layers of a CLIP ViT-H/14 vision encoder.
  arXiv  Detail & Related papers  (2026-05-29T23:51:35Z)
• The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive [0.0]
  CPU-only scoring primitive runs at 2.6 microseconds per token.<n> token rank-frequency distributions converge to the same two- parameter Mandelbrot ranking distribution.<n>We derive a single-pass scoring primitive that composes with model log probabilities when available and degrades to a rank-only mode usable on closed APIs.
  arXiv  Detail & Related papers  (2026-04-28T13:35:31Z)
• D3R-Net: Dual-Domain Denoising Reconstruction Network for Robust Industrial Anomaly Detection [0.0]
  Unsupervised anomaly detection (UAD) is a key ingredient of automated visual inspection in modern manufacturing.<n>We introduce D3R-Net, a Dual-Domain Denoising Reconstruction framework that couples a self-supervised 'healing' task with frequency-aware regularization.<n>In addition to the spatial mean squared error, we employ a Fast Fourier Transform (FFT) magnitude loss that encourages consistency in the frequency domain.
  arXiv  Detail & Related papers  (2026-01-27T23:21:59Z)
• CoV: Chain-of-View Prompting for Spatial Reasoning [64.77921266428824]
  Chain-of-View (CoV) prompting transforms a vision--language model into an active viewpoint reasoner.<n>We evaluate CoV on OpenEQA and obtain an average +11.56% improvement in LLM-Match, with a maximum gain of +13.62% on Qwen3-VL-Flash.
  arXiv  Detail & Related papers  (2026-01-08T17:59:42Z)
• LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning [73.90466023069125]
  We propose LOVE-R1, a model that can adaptively zoom in on a video clip.<n>The model is first provided with densely sampled frames but in a small resolution.<n>If some spatial details are needed, the model can zoom in on a clip of interest with a large frame resolution.
  arXiv  Detail & Related papers  (2025-09-29T13:43:55Z)
• Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors [117.61449210940955]
  We propose an efficient abnormal event detection model based on a lightweight masked auto-encoder (AE) applied at the video frame level. We introduce an approach to weight tokens based on motion gradients, thus shifting the focus from the static background scene to the foreground objects. We generate synthetic abnormal events to augment the training videos, and task the masked AE model to jointly reconstruct the original frames.
  arXiv  Detail & Related papers  (2023-06-21T06:18:05Z)
• VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation [61.660040308290796]
  VideoFlow is a novel optical flow estimation framework for videos. We first propose a TRi-frame Optical Flow (TROF) module that estimates bi-directional optical flows for the center frame in a three-frame manner. With the iterative flow estimation refinement, the information fused in individual TROFs can be propagated into the whole sequence via MOP.
  arXiv  Detail & Related papers  (2023-03-15T03:14:30Z)
• U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Threshold [0.40964539027092906]
  We propose a one-class self-supervised method for anomaly segmentation in images. It benefits from a modern machine learning approach and a more classic statistical detection theory. The proposed approach produces state-of-the-art results for all metrics and all datasets.
  arXiv  Detail & Related papers  (2022-11-22T15:43:19Z)
• Pruning Self-attentions into Convolutional Layers in Single Path [89.55361659622305]
  Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. We propose Single-Path Vision Transformer pruning (SPViT) to efficiently and automatically compress the pre-trained ViTs. Our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously.
  arXiv  Detail & Related papers  (2021-11-23T11:35:54Z)
• FOVEA: Foveated Image Magnification for Autonomous Navigation [53.69803081925454]
  We propose an attentional approach that elastically magnifies certain regions while maintaining a small input canvas. Our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning. On the autonomous driving datasets Argoverse-HD and BDD100K, we show our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning.
  arXiv  Detail & Related papers  (2021-08-27T03:07:55Z)

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.