Search Results for author:
Found 17 papers, 15 papers with code
Attention Prompt Tuning: Parameter-efficient Adaptation of Pre-trained Models for Spatiotemporal Modeling
This approach greatly reduces the number of learnable parameters compared to full tuning.
Guarding Barlow Twins Against Overfitting with Mixed Samples
Self-supervised Learning (SSL) aims to learn transferable feature representations for downstream applications without relying on labeled data.
Ranked #1 on
Self-Supervised Learning
on STL-10
$CrowdDiff$: Multi-hypothesis Crowd Density Estimation using Diffusion Models
Furthermore, as the intermediate time steps of the diffusion process are noisy, we incorporate a regression branch for direct crowd estimation only during training to improve the feature learning.
Deep Metric Learning for Unsupervised Remote Sensing Change Detection
This loss is motivated by the principle of metric learning where we simultaneously maximize the distance between change pair-wise pixels while minimizing the distance between no-change pair-wise pixels in bi-temporal image domain and their deep feature domain.
Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models
We also introduce a novel reliability parameter that allows using different off-the-shelf diffusion models trained across various datasets during sampling time alone to guide it to the desired outcome satisfying multiple constraints.
Ranked #1 on
Face Sketch Synthesis
on Multi-Modal CelebA-HQ
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders
Our adaptive masking strategy samples visible tokens based on the semantic context using an auxiliary sampling network.
Ranked #1 on
Action Classification
on Something-Something V2
DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change Detection
However, in this work, our focus is not on image synthesis but on utilizing it as a pre-trained feature extractor for the downstream application of change detection.
Ranked #1 on
Change Detection
on DSIFN-CD
Orientation-guided Graph Convolutional Network for Bone Surface Segmentation
Due to imaging artifacts and low signal-to-noise ratio in ultrasound images, automatic bone surface segmentation networks often produce fragmented predictions that can hinder the success of ultrasound-guided computer-assisted surgical procedures.
Image Generation with Multimodal Priors using Denoising Diffusion Probabilistic Models
Based on the fact that the distribution over each time step in the diffusion model is Gaussian, in this work we show that there exists a closed-form expression to the generate the image corresponds to the given modalities.
SAR Despeckling using a Denoising Diffusion Probabilistic Model
The despeckled image is recovered by a reverse process which iteratively predicts the added noise using a noise predictor which is conditioned on the speckled image.
SAR Despeckling Using Overcomplete Convolutional Networks
We show that the proposed network improves despeckling performance compared to recent despeckling methods on synthetic and real SAR images.
Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images
The performance of existing deep supervised CD methods is attributed to the large amounts of annotated data used to train the networks.
Ranked #3 on
Semi-supervised Change Detection
on LEVIR-CD - 5% labeled data
(IoU metric)
HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening
Existing pansharpening approaches neglect using an attention mechanism to transfer HR texture features from PAN to LR-HSI features, resulting in spatial and spectral distortions.
Transformer-based SAR Image Despeckling
Synthetic Aperture Radar (SAR) images are usually degraded by a multiplicative noise known as speckle which makes processing and interpretation of SAR images difficult.
A Transformer-Based Siamese Network for Change Detection
This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images.
Ranked #15 on
Change Detection
on LEVIR-CD
SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving
Using just convolution neural networks (ConvNets) for this problem is not effective as it is inefficient at capturing distant dependencies between road segments in the image which is essential to extract road connectivity.
Ranked #1 on
Road Segmentation
on DeepGlobe
Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction
To estimate the PAN image of the up-sampled HSI, we also propose a learnable spectral response function (SRF).
Ranked #1 on
Image Super-Resolution
on Chikusei Dataset
