Related papers: CSAKD: Knowledge Distillation with Cross Self-Atte…
Unstructured pruning remains a powerful strategy for compressing deep neural networks, yet it often demands iterative train-prune-retrain cycles, resulting in significant computational overhead. To address this challenge, we introduce a…
Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss functions. However, due to the difference in feature distributions between the…
High-dimensional hyperspectral imaging (HSI) enables the visualization of ultrafast molecular dynamics and complex, heterogeneous spectra. However, applying this capability to resolve spatially varying vibrational couplings in…
Hyperspectral image (HSI) and SAR/LiDAR data offer complementary spectral and structural information for land-cover classification. However, their effective fusion remains challenging due to two major limitations: The spectral redundancy in…
In this paper, we propose a method using a three dimensional convolutional neural network (3-D-CNN) to fuse together multispectral (MS) and hyperspectral (HS) images to obtain a high resolution hyperspectral image. Dimensionality reduction…
Recent advances in 3D object detection (3DOD) have obtained remarkably strong results for LiDAR-based models. In contrast, surround-view 3DOD models based on multiple camera images underperform due to the necessary view transformation of…
Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and…
Image Super-Resolution (SR) provides a promising technique to enhance the image quality of low-resolution optical sensors, facilitating better-performing target detection and autonomous navigation in a wide range of robotics applications.…
Multimodal sentiment analysis (MSA) systems leverage information from different modalities to predict human sentiment intensities. Incomplete modality is an important issue that may cause a significant performance drop in MSA systems. By…
Leveraging LiDAR-based detectors or real LiDAR point data to guide monocular 3D detection has brought significant improvement, e.g., Pseudo-LiDAR methods. However, the existing methods usually apply non-end-to-end training strategies and…
Automatic segmentation of the prostate cancer from the multi-modal magnetic resonance images is of critical importance for the initial staging and prognosis of patients. However, how to use the multi-modal image features more efficiently is…
Fusing a low-resolution hyperspectral image (HSI) and a high-resolution multispectral image (MSI) of the same scene leads to a super-resolution image (SRI), which is information rich spatially and spectrally. In this paper, we super-resolve…
High-spatial-resolution hyperspectral images (HSI) are essential for applications such as remote sensing and medical imaging, yet HSI sensors inherently trade spatial detail for spectral richness. Fusing high-spatial-resolution…
Given the high availability of data collected by different remote sensing instruments, the data fusion of multi-spectral and hyperspectral images (HSI) is an important topic in remote sensing. In particular, super-resolution as a data…
The application of compressed sensing (CS)-enabled data reconstruction for accelerating magnetic resonance imaging (MRI) remains a challenging problem. This is due to the fact that the information lost in k-space from the acceleration mask…
Knowledge distillation (KD) has enabled remarkable progress in model compression and knowledge transfer. However, KD requires a large volume of original data or their representation statistics that are not usually available in practice.…
Knowledge Distillation has shown very promising abil-ity in transferring learned representation from the largermodel (teacher) to the smaller one (student).Despitemany efforts, prior methods ignore the important role ofretaining…
In this work we present a novel methodology that combines Higher Order Singular Value Decomposition (HOSVD) with Deep Learning (DL) techniques for super-resolution in computational fluid dynamics (CFD) and sparse experimental datasets. This…
Monocular 3D object detection is an inherently ill-posed problem, as it is challenging to predict accurate 3D localization from a single image. Existing monocular 3D detection knowledge distillation methods usually project the LiDAR onto…
Large-scale pre-trained language models (PLMs) have shown great potential in natural language processing tasks. Leveraging the capabilities of PLMs to enhance automatic speech recognition (ASR) systems has also emerged as a promising…