# See More, Detect Less? Taming Information Leakage in Multi-View Anomaly Detection

arXiv: https://arxiv.org/abs/2608.25168 · HTML: https://mlsanity.com/paper/2608.25168/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [A Unified Model for Multi-class Anomaly Detection](https://mlsanity.com/paper/2206.03687/) (2022)
- [DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection](https://mlsanity.com/paper/2211.11317/) (2022)
- [RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection](https://mlsanity.com/paper/2403.05897/) (2024)
- [AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model](https://mlsanity.com/paper/2312.05767/) (2023)
- [AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP](https://mlsanity.com/paper/2503.06661/) (2025)
- [ReLU2 Wins: Discovering Efficient Activation Functions for Sparse LLMs](https://mlsanity.com/paper/2402.03804/) (2024)
- [AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2](https://mlsanity.com/paper/2405.14529/) (2024)
- [UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection](https://mlsanity.com/paper/2412.03342/) (2024)
- [MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects](https://mlsanity.com/paper/2412.04867/) (2024)
- [Learning Multi-view Anomaly Detection with Efficient Adaptive Selection](https://mlsanity.com/paper/2407.11935/) (2024)
- [Unlocking the Potential of Reverse Distillation for Anomaly Detection](https://mlsanity.com/paper/2412.07579/) (2024)
- [AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation](https://mlsanity.com/paper/2507.19949/) (2025)
- [ROADS: Robust Prompt-driven Multi-Class Anomaly Detection under Domain Shift](https://mlsanity.com/paper/2411.16049/) (2024)
- [Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation](https://mlsanity.com/paper/2503.04151/) (2025)

## Abstract (arXiv)

In multi-view anomaly detection, more cross-view information can actually hurt. When multiple inspection views are naively fused in a reconstruction-based pipeline, normal cues from intact views propagate to the decoder, which faithfully reconstructs anomalous regions, collapsing the reconstruction gap the detector depends on. We call this failure mode cross-view information leakage and show that effective multi-view fusion must explicitly restrict the information reaching the decoder. Building on this insight, we present GLAD(Global-Local Attention Driven framework), the first framework combining vision foundation model features with local and global cross-view fusion for multi-view anomaly detection. The Multi-view Merging Attention (MMA) module performs local cross-view fusion at linear complexity with learnable view importance weighting and token-wise gating, letting each view selectively incorporate fine-grained evidence from other views at O(N) cost. The Object-Guided Attention (OGA) module captures global context by aggregating class tokens from all views into a single object-level representation and broadcasting it back to patch tokens via temperature-scaled sigmoid gating, replacing the original patch representations rather than adding a residual to preserve the reconstruction gap. Experiments on Real-IAD and MANTA-Tiny show that GLAD outperforms state-of-the-art methods across sample-, image-, and pixel-level metrics, confirming that principled information restriction is key to multi-view anomaly reasoning.