4 papers
MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models
Yuncheng Yang, Feiyang Ye, Shixian Luo +7
Vision-Language Models (VLMs) have achieved success using homogeneous Transformers to process multimedia data. Recent studies show that heterogeneous structures interleaving effici…
Efficient Hyperspectral Image Reconstruction Using Lightweight Separate Spectral Transformers
Jianan Li, Wangcai Zhao, Tingfa Xu
Hyperspectral imaging (HSI) is essential across various disciplines for its capacity to capture rich spectral information. However, efficiently reconstructing hyperspectral images…
Spectral-wise Implicit Neural Representation for Hyperspectral Image Reconstruction
Huan Chen, Wangcai Zhao, Tingfa Xu +3
Coded Aperture Snapshot Spectral Imaging (CASSI) reconstruction aims to recover the 3D spatial-spectral signal from 2D measurement. Existing methods for reconstructing Hyperspectra…
Mixed-granularity Implicit Representation for Continuous Hyperspectral Compressive Reconstruction
Jianan Li, Huan Chen, Wangcai Zhao +2
Hyperspectral Images (HSIs) are crucial across numerous fields but are hindered by the long acquisition times associated with traditional spectrometers. The Coded Aperture Snapshot…