Hierarchical Fusion and Joint Aggregation: A Multi-Level Feature Representation Method for AIGC Image Quality Assessment
The quality assessment of AI-generated content (AIGC) faces multi-dimensional challenges, that span from low-level visual perception to high-level semantic understanding. Existing methods generally rely on single-level visual features, limiting their ability to capture complex distortions in AIGC images. To address this limitation, a multi-level visual representation paradigm is proposed with three stages, namely multi-level feature extraction, hierarchical fusion, and joint aggregation. Based on this paradigm, two networks are developed. Specifically, the Multi-Level Global-Local Fusion Network (MGLF-Net) is designed for the perceptual quality assessment, extracting complementary local and global features via dual CNN and Transformer visual backbones. The Multi-Level Prompt-Embedded Fusion Network (MPEF-Net) targets Text-to-Image correspondence by embedding prompt semantics into the visual feature fusion process at each feature level. The fused multi-level features are then aggregated for final evaluation. Experiments on benchmarks demonstrate outstanding performance on both tasks, validating the effectiveness of the proposed multi-level visual assessment paradigm.
Code (0)
등록된 구현이 없습니다.
Tasks
Image Quality AssessmentSimilar Papers 제목 키워드 기반
Bi-level Dynamic Learning for Jointly Multi-modality Image Fusion and Beyond
Recently, multi-modality scene perception tasks, e.g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems. However, early efforts always consider boosting a single ta…
Scene UnderstandingProbabilistic Hierarchical Forecasting with Deep Poisson Mixtures
Hierarchical forecasting problems arise when time series have a natural group structure, and predictions at multiple levels of aggregation and disaggregation across the groups are needed. In such problems, it is often de…
Time SeriesTime Series AnalysisMulti-Person Pose Estimation with Enhanced Feature Aggregation and Selection
We propose a novel Enhanced Feature Aggregation and Selection network (EFASNet) for multi-person 2D human pose estimation. Due to enhanced feature representation, our method can well handle crowded, cluttered and occlude…
2D Human Pose EstimationKeypoint DetectionMulti-Person Pose EstimationPose EstimationCo-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation
Skeleton-based human action recognition has recently drawn increasing attentions with the availability of large-scale skeleton datasets. The most crucial factors for this task lie in two aspects: the intra-frame represen…
Action RecognitionRF-based Pose EstimationSkeleton Based Action RecognitionTemporal Action LocalizationHiMatch-AD: DINOv3-driven Hierarchical Matching for Training-free Medical Anomaly Detection
Anomaly detection is essential for medical image analysis, where pathological regions often appear as rare deviations from normal anatomical structures. While training-based methods have achieved promising performance, t…
Anomaly Detection