Search Results for author:
Found 18 papers, 11 papers with code
FLD+: Data-efficient Evaluation Metric for Generative Models
We introduce a new metric to assess the quality of generated images that is more reliable, data-efficient, compute-efficient, and adaptable to new domains than the previous metrics, such as Fr\'echet Inception Distance (FID).
Evaluation Metric for Quality Control and Generative Models in Histopathology Images
Our study introduces ResNet-L2 (RL2), a novel metric for evaluating generative models and image quality in histopathology, addressing limitations of traditional metrics, such as Frechet inception distance (FID), when the data is scarce.
Normalizing Flow-Based Metric for Image Generation
This property gives the proposed metrics a few advantages over the widely used Fr\'echet inception distance (FID) and other recent metrics.
Ranked #1 on
Image Generation
on CelebA-HQ
FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch
We introduce Federated Learning with Enhanced Nesterov-Newton Sketch (FLeNS), a novel method that harnesses both the acceleration capabilities of Nesterov's method and the dimensionality reduction benefits of Hessian sketching.
EDSNet: Efficient-DSNet for Video Summarization
Current video summarization methods largely rely on transformer-based architectures, which, due to their quadratic complexity, require substantial computational resources.
WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures.
Ranked #1 on
Image Super-Resolution
on BSD100 - 2x upscaling
Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision
In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as feature extractors.
Ranked #1 on
Image Classification
on BreakHis
(using extra training data)
Breast Cancer Histology Image Classification
Decision Making
+3
Advancing Gene Selection in Oncology: A Fusion of Deep Learning and Sparsity for Precision Gene Selection
Gene selection plays a pivotal role in oncology research for improving outcome prediction accuracy and facilitating cost-effective genomic profiling for cancer patients.
Heterogeneous graphs model spatial relationships between biological entities for breast cancer diagnosis
The heterogeneity of breast cancer presents considerable challenges for its early detection, prognosis, and treatment selection.
WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting
The current state-of-the-art models for image inpainting are computationally heavy as they are based on transformer or CNN backbones that are trained in adversarial or diffusion settings.
Ranked #1 on
Image Inpainting
on ImageNet
WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution
We propose a new neural network -- WaveMixSR -- for image super-resolution based on WaveMix architecture which uses a 2D-discrete wavelet transform for spatial token-mixing.
Ranked #2 on
Image Super-Resolution
on BSD100 - 2x upscaling
CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation
We propose a new technique called CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation.
Ranked #1 on
Unsupervised Domain Adaptation
on FHIST
Magnification Invariant Medical Image Analysis: A Comparison of Convolutional Networks, Vision Transformers, and Token Mixers
Convolution Neural Networks (CNNs) are widely used in medical image analysis, but their performance degrade when the magnification of testing images differ from the training images.
Ranked #3 on
Image Classification
on BreakHis
Breast Cancer Histology Image Classification
Deep Learning
+2
WaveMix: A Resource-efficient Neural Network for Image Analysis
The whole architecture is a stack of self-similar and resolution-preserving WaveMix blocks, which allows architectural flexibility for various tasks and levels of resource availability.
Ranked #1 on
Image Classification
on Galaxy10 DECals
(using extra training data)
WaveMix: Resource-efficient Token Mixing for Images
The multi-scale nature of the DWT also reduces the requirement for a deeper architecture compared to the CNNs, as the latter relies on pooling for partial spatial mixing.
Ranked #15 on
Image Classification
on MNIST
Convolutional Xformers for Vision
Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks.
Ranked #22 on
Image Classification
on Tiny ImageNet Classification
"So You Think You're Funny?": Rating the Humour Quotient in Standup Comedy
We devise a novel scoring mechanism to annotate the training data with a humour quotient score using the audience's laughter.
Vision Xformers: Efficient Attention for Image Classification
Secondly, we introduced an inductive bias for images by replacing the initial linear embedding layer by convolutional layers in ViX, which significantly increased classification accuracy without increasing the model size.
Ranked #238 on
Image Classification
on CIFAR-10
(using extra training data)
