MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects
We present MANTA, a visual-text anomaly detection dataset for tiny objects. The visual component comprises over 137.3K images across 38 object categories spanning five typical domains, of which 8.6K images are labeled as anomalous with pixel-level annotations. Each image is captured from five distinct viewpoints to ensure comprehensive object coverage. The text component consists of two subsets: Declarative Knowledge, including 875 words that describe common anomalies across various domains and specific categories, with detailed explanations for < what, why, how>, including causes and visual characteristics; and Constructivist Learning, providing 2K multiple-choice questions with varying levels of difficulty, each paired with images and corresponded answer explanations. We also propose a baseline for visual-text tasks and conduct extensive benchmarking experiments to evaluate advanced methods across different settings, highlighting the challenges and efficacy of our dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
2kAnomaly DetectionBenchmarkingMultiple-choiceSimilar Papers 제목 키워드 기반
Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided Alignment
Unsupervised visual anomaly detection from multi-view images presents a significant challenge: distinguishing genuine defects from benign appearance variations caused by viewpoint changes. Existing methods, often designe…
Anomaly DetectionMANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
Large language model-based multi-agent systems improve complex problem solving through task decomposition, agent specialization, information exchange, and intermediate validation. However, existing systems typically trea…
Mathematical ReasoningRobust Re-identification of Manta Rays from Natural Markings by Learning Pose Invariant Embeddings
Visual identification of individual animals that bear unique natural body markings is an important task in wildlife conservation. The photo databases of animal markings grow larger and each new observation has to be matc…
TripletMANTA: Physics-Informed Generalized Underwater Object Tracking
Underwater object tracking is challenging due to wavelength dependent attenuation and scattering, which severely distort appearance across depths and water conditions. Existing trackers trained on terrestrial data fail t…
Representation LearningContrastive LearningObject TrackingContent-aware Warping for View Synthesis
Existing image-based rendering methods usually adopt depth-based image warping operation to synthesize novel views. In this paper, we reason the essential limitations of the traditional warping operation to be the limite…
Novel View Synthesis