SPG: Sparse-Projected Guides with Sparse Autoencoders for Zero-Shot Anomaly Detection

2026-04-03 · Tomoyasu Nanaumi, Yukino Tsuzuki, Junichi Okubo, Junichiro Fujii, Takayoshi Yamashita arxiv

We study zero-shot anomaly detection and segmentation using frozen foundation model features, where all learnable parameters are trained only on a labeled auxiliary dataset and deployed to unseen target categories without any target-domain adaptation. Existing prompt-based approaches use handcrafted or learned prompt embeddings as reference vectors for normal/anomalous states. We propose Sparse-Projected Guides (SPG), a prompt-free framework that learns sparse guide coefficients in the Sparse Autoencoder (SAE) latent space, which generate normal/anomaly guide vectors via the SAE dictionary. SPG employs a two stage learning strategy on the labeled auxiliary dataset: (i) train an SAE on patch-token features, and (ii) optimize only guide coefficients using auxiliary pixel-level masks while freezing the backbone and SAE. On MVTec AD and VisA under cross-dataset zero-shot settings, SPG achieves competitive image-level detection and strong pixel-level segmentation; with DINOv3, SPG attains the highest pixellevel AUROC among the compared methods. We also report SPG instantiated with OpenCLIP (ViT-L/14@336px) to align the backbone with CLIP-based baselines. Moreover, the learned guide coefficients trace decisions back to a small set of dictionary atoms, revealing category-general and category-specific factors.

📄 PDF Abstract BibTeX arXiv:2604.02871

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection Domain Adaptation

Binary Sparse Coding for Interpretability

2025-09-29 · Lucia Quirke, Stepan Shabalin, Nora Belrose arxiv

Sparse autoencoders (SAEs) are used to decompose neural network activations into sparsely activating features, but many SAE features are only interpretable at high activation strengths. To address this issue we propose t…

Design of an basis-projected layer for sparse datasets in deep learning training using gc-ms spectra as a case study

2024-03-14 · Yu Tang Chang, Shih Fang Chen

Deep learning (DL) models encompass millions or even billions of parameters and learn complex patterns from big data. However, not all data are initially stored in a suitable formation to effectively train a DL model, e.…

Image Compression: Sparse Coding vs. Bottleneck Autoencoders

2017-10-26 · Yijing Watkins, Mohammad Sayeh, Oleksandr Iaroshenko, Garrett Kenyon

Bottleneck autoencoders have been actively researched as a solution to image compression tasks. However, we observed that bottleneck autoencoders produce subjectively low quality reconstructed images. In this work, we ex…

General Classification Image Compression SSIM

Unlocking the Address Book: Dissecting the Sparse Semantic Structure of LLM Key-Value Caches via Sparse Autoencoders

2025-12-11 · Qingsen Ma, Dianyun Wang, Jiaming Lyu, Yaoye Wang 외 arxiv

The Key-Value (KV) cache is the primary memory bottleneck in long-context Large Language Models, yet it is typically treated as an opaque numerical tensor. In this work, we propose \textbf{STA-Attention}, a framework tha…

Sparse Autoencoders for Interpretable Medical Image Representation Learning

2026-03-24 · Philipp Wesp, Robbie Holland, Vasiliki Sideri-Lampretsa, Sergios Gatidis arxiv

Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this s…

Dimensionality Reduction Representation Learning Image Retrieval