Search Results for author:
Found 40 papers, 9 papers with code
RFWNet: A Lightweight Remote Sensing Object Detector Integrating Multi-Scale Receptive Fields and Foreground Focus Mechanism
Challenges in remote sensing object detection (RSOD), such as high inter-class similarity, imbalanced foreground-background distribution, and the small size of objects in remote sensing images significantly hinder detection accuracy.
ChatMotion: A Multimodal Multi-Agent for Human Motion Analysis
Advancements in Multimodal Large Language Models (MLLMs) have improved human motion understanding.
COEF-VQ: Cost-Efficient Video Quality Understanding through a Cascaded Multimodal LLM Framework
In this paper, we propose COEF-VQ, a novel cascaded MLLM framework for better video quality understanding on TikTok.
Diff5T: Benchmarking Human Brain Diffusion MRI with an Extensive 5.0 Tesla K-Space and Spatial Dataset
Diffusion magnetic resonance imaging (dMRI) provides critical insights into the microstructural and connectional organization of the human brain.
LaVIDE: A Language-Vision Discriminator for Detecting Changes in Satellite Image with Map References
Change detection, which typically relies on the comparison of bi-temporal images, is significantly hindered when only a single image is available.
Graph Canvas for Controllable 3D Scene Generation
Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension.
Human Motion Instruction Tuning
This paper presents LLaMo (Large Language and Human Motion Assistant), a multimodal framework for human motion instruction tuning.
Adaptive Masking Enhances Visual Grounding
In recent years, zero-shot and few-shot learning in visual grounding have garnered considerable attention, largely due to the success of large-scale vision-language pre-training on expansive datasets such as LAION-5B and DataComp-1B.
MR Optimized Reconstruction of Simultaneous Multi-Slice Imaging Using Diffusion Model
Diffusion model has been successfully applied to MRI reconstruction, including single and multi-coil acquisition of MRI data.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
Knowledge-driven deep learning for fast MR imaging: undersampled MR image reconstruction from supervised to un-supervised learning
The traits and trends of these techniques have also been given which have shifted from supervised learning to semi-supervised learning, and finally, to unsupervised learning methods.
Physics-Informed DeepMRI: Bridging the Gap from Heat Diffusion to k-Space Interpolation
In order to enhance interpretability and overcome the acceleration limitations, this paper introduces an interpretable framework that unifies both $k$-space interpolation techniques and image-domain methods, grounded in the physical principles of heat diffusion equations.
SPIRiT-Diffusion: Self-Consistency Driven Diffusion Model for Accelerated MRI
To overcome this challenge, we introduce a novel approach called SPIRiT-Diffusion, which is a diffusion model for k-space interpolation inspired by the iterative self-consistent SPIRiT method.
SPIRiT-Diffusion: SPIRiT-driven Score-Based Generative Modeling for Vessel Wall imaging
Diffusion model is the most advanced method in image generation and has been successfully applied to MRI reconstruction.
K-UNN: k-Space Interpolation With Untrained Neural Network
Recently, untrained neural networks (UNNs) have shown satisfactory performances for MR image reconstruction on random sampling trajectories without using additional full-sampled training data.
SelfCoLearn: Self-supervised collaborative learning for accelerating dynamic MR imaging
Lately, deep learning has been extensively investigated for accelerating dynamic magnetic resonance (MR) imaging, with encouraging progresses achieved.
Attention mechanism-based generative adversarial networks for cloud removal in Landsat images
First, attention maps of the input cloudy images are generated to extract the cloud distributions and features through an attentive recurrent network.
Multiscale Convolutional Transformer with Center Mask Pretraining for Hyperspectral Image Classification
However, CNN-based methods are difficult to capture long-range dependencies, and also require a large amount of labeled data for model training. Besides, most of the self-supervised training methods in the field of HSI classification are based on the reconstruction of input samples, and it is difficult to achieve effective use of unlabeled samples.
Equilibrated Zeroth-Order Unrolled Deep Networks for Accelerated MRI
Specifically, focusing on accelerated MRI, we unroll a zeroth-order algorithm, of which the network module represents the regularizer itself, so that the network output can be still covered by the regularization model.
A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled Samples
In general, deep learning models often contain many trainable parameters and require a massive number of labeled samples to achieve optimal performance.
Simpler Does It: Generating Semantic Labels with Objectness Guidance
Extensive experiments demonstrate the high quality of our generated pseudo-labels and effectiveness of the proposed framework in a variety of domains.
Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs
In this paper, we challenge the common assumption that collapsing the spatial dimensions of a 3D (spatial-channel) tensor in a convolutional neural network (CNN) into a vector via global pooling removes all spatial information.
Deep Amended Gradient Descent for Efficient Spectral Reconstruction from Single RGB Images
Then, we design a lightweight neural network with a multi-stage architecture to mimic the formed amended gradient descent process, in which efficient convolution and novel spectral zero-mean normalization are proposed to effectively extract spatial-spectral features for regressing an initialization, a basic gradient, and an incremental gradient.
Multi-Attention Generative Adversarial Network for Remote Sensing Image Super-Resolution
The main body of the generator contains two blocks; one is the pyramidal convolution in the residual-dense block (PCRDB), and the other is the attention-based upsample (AUP) block.
SRR-Net: A Super-Resolution-Involved Reconstruction Method for High Resolution MR Imaging
Improving the image resolution and acquisition speed of magnetic resonance imaging (MRI) is a challenging problem.
Deep Manifold Learning for Dynamic MR Imaging
The nonlinear manifold is designed to characterize the temporal correlation of dynamic signals.
Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
; (ii) Does position encoding affect the learning of semantic representations?
Shape or Texture: Understanding Discriminative Features in CNNs
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a `texture bias': given an image with both texture and shape cues (e. g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture.
Boundary Effects in CNNs: Feature or Bug?
Finally, we demonstrate the implications of these findings on a number of real-world tasks to show that position information can act as a feature or a bug.
Shape or Texture: Disentangling Discriminative Features in CNNs
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a 'texture bias': given an image with both texture and shape cues (e. g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture.
Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications
Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions.
Deep Low-rank plus Sparse Network for Dynamic MR Imaging
However, the selection of the parameters of L+S is empirical, and the acceleration rate is limited, which are common failings of iterative compressed sensing MR imaging (CS-MRI) reconstruction methods.
Deep Low-rank Prior in Dynamic MR Imaging
The deep learning methods have achieved attractive performance in dynamic MR cine imaging.
Revisiting Saliency Metrics: Farthest-Neighbor Area Under Curve
Our experiment shows FN-AUC can measure spatial biases, central and peripheral, more effectively than S-AUC without penalizing the fixation locations.
How Much Position Information Do Convolutional Neural Networks Encode?
In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent.
Deep Metric Learning-Based Feature Embedding for Hyperspectral Image Classification
In the first task, when only a few labeled samples are available, we employ ideas from metric learning based on deep embedding features and make a similarity learning between pairs of samples.
Few-Shot Image Classification
Hyperspectral Image Classification
+4
Richer and Deeper Supervision Network for Salient Object Detection
Recent Salient Object Detection (SOD) systems are mostly based on Convolutional Neural Networks (CNNs).
DIMENSION: Dynamic MR Imaging with Both K-space and Spatial Prior Knowledge Obtained via Multi-Supervised Network Training
Dynamic MR image reconstruction from incomplete k-space data has generated great research interest due to its capability in reducing scan time.
Right for the Right Reason: Training Agnostic Networks
We consider the problem of a neural network being requested to classify images (or other inputs) without making implicit use of a "protected concept", that is a concept that should not play any role in the decision of the network.
EML-NET:An Expandable Multi-Layer NETwork for Saliency Prediction
Furthermore, the encoder can contain more than one CNN model to extract features, and models can have different architectures or be pre-trained on different datasets.
