Search Results for author:
Found 26 papers, 16 papers with code
Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers
As these parameters are independent, a single diffusion model with these task-specific parameters can be used to perform multiple tasks simultaneously.
MaxFusion: Plug&Play Multi-Modal Generation in Text-to-Image Diffusion Models
Large diffusion-based Text-to-Image (T2I) models have shown impressive generative powers for text-to-image generation as well as spatially conditioned image generation.
CheXagent: Towards a Foundation Model for Chest X-Ray Interpretation
However, developing FMs that can accurately interpret CXRs is challenging due to the (1) limited availability of large-scale vision-language datasets in the medical image domain, (2) lack of vision and language encoders that can capture the complexities of medical data, and (3) absence of evaluation frameworks for benchmarking the abilities of FMs on CXR interpretation.
Disruptive Autoencoders: Leveraging Low-level features for 3D Medical Image Pre-training
We curate a large-scale dataset to enable pre-training of 3D medical radiology images (MRI and CT).
Ambiguous Medical Image Segmentation using Diffusion Models
Collective insights from a group of experts have always proven to outperform an individual's best diagnostic for clinical tasks.
ReBotNet: Fast Real-time Video Enhancement
The first branch learns spatio-temporal features by tokenizing the input frames along the spatial and temporal dimensions using a ConvNext-based encoder and processing these abstract tokens using a bottleneck mixer.
CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition
Attempting to train the visual and text encoder to account for this shift results in catastrophic forgetting and a notable decrease in performance.
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.
Simultaneous Bone and Shadow Segmentation Network using Task Correspondence Consistency
Segmenting both bone surface and the corresponding acoustic shadow are fundamental tasks in ultrasound (US) guided orthopedic procedures.
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.
Target and Task specific Source-Free Domain Adaptive Image Segmentation
In task-specific adaptation, we exploit the enhanced pseudo-labels using a student-teacher framework to effectively learn segmentation on the target domain.
Interactive Portrait Harmonization
To enable flexible interaction between user and harmonization, we introduce interactive harmonization, a new setting where the harmonization is performed with respect to a selected \emph{region} in the reference image instead of the entire background.
On-the-Fly Test-time Adaptation for Medical Image Segmentation
During test-time, the model takes in just the new test image and generates a domain code to adapt the features of source model according to the test data.
UNeXt: MLP-based Rapid Medical Image Segmentation Network
Using tokenized MLPs in latent space reduces the number of parameters and computational complexity while being able to result in a better representation to help segmentation.
Ranked #3 on
Medical Image Segmentation
on ISIC 2018
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.
TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions
We also introduce a transformer decoder with learnable weather type embeddings to adjust to the weather degradation at hand.
Ranked #1 on
Single Image Deraining
on Raindrop
Fine-Context Shadow Detection using Shadow Removal
First, we propose a Fine Context-aware Shadow Detection Network (FCSD-Net), where we constraint the receptive field size and focus on low-level features to learn fine context features better.
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
Image Fusion Transformer
Furthermore, we show the effectiveness of the proposed ST fusion strategy with an ablation analysis.
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
Over-and-Under Complete Convolutional RNN for MRI Reconstruction
Reconstructing magnetic resonance (MR) images from undersampled data is a challenging problem due to various artifacts introduced by the under-sampling operation.
Medical Transformer: Gated Axial-Attention for Medical Image Segmentation
The proposed Medical Transformer (MedT) is evaluated on three different medical image segmentation datasets and it is shown that it achieves better performance than the convolutional and other related transformer-based architectures.
Ranked #1 on
Medical Image Segmentation
on Brain US
Overcomplete Representations Against Adversarial Videos
Adversarial robustness of deep neural networks is an extensively studied problem in the literature and various methods have been proposed to defend against adversarial images.
Overcomplete Deep Subspace Clustering Networks
This method uses undercomplete representations of the input data which makes it not so robust and more dependent on pre-training.
Exploring Overcomplete Representations for Single Image Deraining using CNNs
Removal of rain streaks from a single image is an extremely challenging problem since the rainy images often contain rain streaks of different size, shape, direction and density.
KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation
To overcome this issue, we propose using an overcomplete convolutional architecture where we project our input image into a higher dimension such that we constrain the receptive field from increasing in the deep layers of the network.
Ranked #1 on
Medical Image Segmentation
on RITE
