ArtifactLens: Hundreds of Labels Are Enough for Artifact Detection with VLMs

• URL: http://arxiv.org/abs/2602.09475v1
• Date: Tue, 10 Feb 2026 07:16:22 GMT
• Title: ArtifactLens: Hundreds of Labels Are Enough for Artifact Detection with VLMs
• Abstract summary: ArtifactLens achieves state-of-the-art on five human artifact benchmarks.<n>We show that pretrained VLMs already encode the knowledge needed to detect artifacts.<n>Our methods generalize to other artifact types - object morphology, animal anatomy, and entity interactions.
• Score: 43.85474845650244
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern image generators produce strikingly realistic images, where only artifacts like distorted hands or warped objects reveal their synthetic origin. Detecting these artifacts is essential: without detection, we cannot benchmark generators or train reward models to improve them. Current detectors fine-tune VLMs on tens of thousands of labeled images, but this is expensive to repeat whenever generators evolve or new artifact types emerge. We show that pretrained VLMs already encode the knowledge needed to detect artifacts - with the right scaffolding, this capability can be unlocked using only a few hundred labeled examples per artifact category. Our system, ArtifactLens, achieves state-of-the-art on five human artifact benchmarks (the first evaluation across multiple datasets) while requiring orders of magnitude less labeled data. The scaffolding consists of a multi-component architecture with in-context learning and text instruction optimization, with novel improvements to each. Our methods generalize to other artifact types - object morphology, animal anatomy, and entity interactions - and to the distinct task of AIGC detection.

Related papers

• IPAD-CLIP: Teaching CLIP to Detect Image Local Perceptual Artifacts [43.42573468235177]
  We formalize the Image Perceptual Artifact Detection (IPAD) task to address this gap.<n>Core challenge of IPAD lies in the localized, subtle, and semantically weak nature of these artifacts.<n>We introduce IPAD-CLIP, a novel framework built upon CLIP that enhances artifact discrimination in both textual and visual spaces.
  arXiv  Detail & Related papers  (2026-05-09T04:04:41Z)
• See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis [17.896266572037348]
  ArtiAgent efficiently creates pairs of real and artifact-injected images.<n>It comprises three agents: a perception agent that recognizes entities and subentities from real images, a synthesis agent that introduces artifacts via artifact injection tools, and a curation agent that filters the synthesized artifacts.
  arXiv  Detail & Related papers  (2026-02-24T14:34:13Z)
• Prominence-Aware Artifact Detection and Dataset for Image Super-Resolution [0.7297638898415074]
  We argue that artifacts should be characterized by their prominence to human observers rather than treated as uniform binary defects.<n>Motivated by this, we present a novel dataset of 1302 artifact examples from 11 contemporary image-SR methods.<n>We train a lightweight regressor that produces spatial prominence heatmaps and outperforms existing methods at detecting prominent artifacts.
  arXiv  Detail & Related papers  (2025-10-19T08:28:53Z)
• LEGION: Learning to Ground and Explain for Synthetic Image Detection [49.958951540410816]
  We introduce SynthScars, a high-quality and diverse dataset consisting of 12,236 fully synthetic images with human-expert annotations.<n>It features 4 distinct image content types, 3 categories of artifacts, and fine-grained annotations covering pixel-level segmentation, detailed textual explanations, and artifact category labels.<n>We propose LEGION, a multimodal large language model (MLLM)-based image forgery analysis framework that integrates artifact detection, segmentation, and explanation.
  arXiv  Detail & Related papers  (2025-03-19T14:37:21Z)
• Zero-Shot Detection of AI-Generated Images [54.01282123570917]
  We propose a zero-shot entropy-based detector (ZED) to detect AI-generated images. Inspired by recent works on machine-generated text detection, our idea is to measure how surprising the image under analysis is compared to a model of real images. ZED achieves an average improvement of more than 3% over the SoTA in terms of accuracy.
  arXiv  Detail & Related papers  (2024-09-24T08:46:13Z)
• MVAD: A Multiple Visual Artifact Detector for Video Streaming [7.154108202395319]
  Visual artifacts are often introduced into streamed video content, due to prevailing conditions during content production and delivery.<n>Existing detection methods often focus on a single type of artifact and determine the presence of an artifact.<n>We propose a Multiple Visual Artifact Detector, MVAD, for video streaming which, for the first time, is able to detect multiple artifacts.
  arXiv  Detail & Related papers  (2024-05-31T21:56:04Z)
• Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detection [105.9932053078449]
  In this work, we show that, on the contrary, the small and training-free filter is sufficient to capture more general artifact representations. Due to its unbias towards both the training and test sources, we define it as Data-Independent Operator (DIO) to achieve appealing improvements on unseen sources. Our detector achieves a remarkable improvement of $13.3%$, establishing a new state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-03-11T15:22:28Z)
• Perceptual Artifacts Localization for Image Synthesis Tasks [59.638307505334076]
  We introduce a novel dataset comprising 10,168 generated images, each annotated with per-pixel perceptual artifact labels. A segmentation model, trained on our proposed dataset, effectively localizes artifacts across a range of tasks. We propose an innovative zoom-in inpainting pipeline that seamlessly rectifies perceptual artifacts in the generated images.
  arXiv  Detail & Related papers  (2023-10-09T10:22:08Z)
• AltFreezing for More General Video Face Forgery Detection [138.5732617371004]
  We propose to capture both spatial and unseen temporal artifacts in one model for face forgery detection. We present a novel training strategy called AltFreezing for more general face forgery detection.
  arXiv  Detail & Related papers  (2023-07-17T08:24:58Z)
• Generalizable Deep Learning Method for Suppressing Unseen and Multiple MRI Artifacts Using Meta-learning [1.376408511310322]
  We propose curriculum-MAML (CMAML), a learning process that integrates MAML with curriculum learning to adaptively learn restoration of multiple artifacts during training. CMAML exhibits better PSNR for 83% of unseen types and amounts of artifacts and improved SSIM in all cases, and (ii) better artifact suppression in 4 out of 5 cases of composite artifacts (scans with multiple artifacts)
  arXiv  Detail & Related papers  (2023-04-13T10:17:34Z)

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.