Search Results for author:
Found 17 papers, 7 papers with code
Fin-Fed-OD: Federated Outlier Detection on Financial Tabular Data
Anomaly detection in real-world scenarios poses challenges due to dynamic and often unknown anomaly distributions, requiring robust methods that operate under an open-world assumption.
ObjBlur: A Curriculum Learning Approach With Progressive Object-Level Blurring for Improved Layout-to-Image Generation
We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes and labels.
Latent Dataset Distillation with Diffusion Models
In response to these limitations, the concept of distilling the information on a dataset into a condensed set of (synthetic) samples, namely a distilled dataset, emerged.
TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax
The quadratic complexity of the attention mechanism represents one of the biggest hurdles for processing long sequences using Transformers.
Diffusion Models, Image Super-Resolution And Everything: A Survey
Diffusion Models (DMs) have disrupted the image Super-Resolution (SR) field and further closed the gap between image quality and human perceptual preferences.
Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers
This benchmark provides a standardized baseline across the landscape of efficiency-oriented transformers and our framework of analysis, based on Pareto optimality, reveals surprising insights.
Ranked #264 on
Image Classification
on ImageNet
Dynamic Attention-Guided Diffusion for Image Super-Resolution
To address this, we introduce "You Only Diffuse Areas" (YODA), a dynamic attention-guided diffusion method for image SR. YODA selectively focuses on spatial regions using attention maps derived from the low-resolution image and the current time step in the diffusion process.
DWA: Differential Wavelet Amplifier for Image Super-Resolution
This work introduces Differential Wavelet Amplifier (DWA), a drop-in module for wavelet-based image Super-Resolution (SR).
Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution
This paper presents a novel Diffusion-Wavelet (DiWa) approach for Single-Image Super-Resolution (SISR).
Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area.
Spatial Transformer Networks for Curriculum Learning
Curriculum learning is a bio-inspired training technique that is widely adopted to machine learning for improved optimization and better training of neural networks regarding the convergence rate or obtained accuracy.
XAI Handbook: Towards a Unified Framework for Explainable AI
The field of explainable AI (XAI) has quickly become a thriving and prolific community.
Contextual Classification Using Self-Supervised Auxiliary Models for Deep Neural Networks
Classification problems solved with deep neural networks (DNNs) typically rely on a closed world paradigm, and optimize over a single objective (e. g., minimization of the cross-entropy loss).
Ranked #89 on
Image Classification
on CIFAR-100
(using extra training data)
Revisiting Sequence-to-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory
Video Object Segmentation (VOS) is an active research area of the visual domain.
P $\approx$ NP, at least in Visual Question Answering
In recent years, progress in the Visual Question Answering (VQA) field has largely been driven by public challenges and large datasets.
What do Deep Networks Like to See?
To do this, an autoencoder (AE) was fine-tuned on gradients from a pre-trained classifier with fixed parameters.
Ranked #818 on
Image Classification
on ImageNet
Adversarial Defense based on Structure-to-Signal Autoencoders
We analyze their robustness against several white-box and gray-box scenarios on the large ImageNet dataset.
