Search Results for author:
Found 23 papers, 10 papers with code
A Study in Dataset Pruning for Image Super-Resolution
We introduce a novel approach that reduces a dataset to a core-set of training samples, selected based on their loss values as determined by a simple pre-trained SR model.
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.
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.
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).
DartsReNet: Exploring new RNN cells in ReNet architectures
We present new Recurrent Neural Network (RNN) cells for image classification using a Neural Architecture Search (NAS) approach called DARTS.
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.
Less is More: Proxy Datasets in NAS approaches
One of our surprising findings is that in most cases we can reduce the amount of training data to 25\%, consequently reducing search time to 25\%, while at the same time maintaining the same accuracy as if training on the full dataset.
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.
A Reinforcement Learning Approach for Sequential Spatial Transformer Networks
Spatial Transformer Networks (STN) can generate geometric transformations which modify input images to improve the classifier's performance.
AudioCLIP: Extending CLIP to Image, Text and Audio
AudioCLIP achieves new state-of-the-art results in the Environmental Sound Classification (ESC) task, out-performing other approaches by reaching accuracies of 90. 07% on the UrbanSound8K and 97. 15% on the ESC-50 datasets.
Ranked #1 on
Environmental Sound Classification
on ESC-50
Combining Transformer Generators with Convolutional Discriminators
Transformer models have recently attracted much interest from computer vision researchers and have since been successfully employed for several problems traditionally addressed with convolutional neural networks.
AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Style
In this paper, we propose a method for attribute controlled image synthesis from layout which allows to specify the appearance of individual objects without affecting the rest of the image.
Adversarial Text-to-Image Synthesis: A Review
With the advent of generative adversarial networks, synthesizing images from textual descriptions has recently become an active research area.
Hybrid-S2S: Video Object Segmentation with Recurrent Networks and Correspondence Matching
In this work, we study an RNN-based architecture and address some of these issues by proposing a hybrid sequence-to-sequence architecture named HS2S, utilizing a dual mask propagation strategy that allows incorporating the information obtained from correspondence matching.
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.
ESResNet: Environmental Sound Classification Based on Visual Domain Models
Environmental Sound Classification (ESC) is an active research area in the audio domain and has seen a lot of progress in the past years.
Ranked #5 on
Environmental Sound Classification
on UrbanSound8K
(using extra training data)
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.
Fusion Strategies for Learning User Embeddings with Neural Networks
In this paper, we run an experiment on movie ratings data, where we analyze the effect on embedding quality caused by several fusion strategies in neural networks.
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
Symbol Grounding Association in Multimodal Sequences with Missing Elements
We evaluated the proposed extension in the following scenarios: missing elements in one modality (visual or audio) and missing elements in both modalities (visual and sound).
Scene Labeling With LSTM Recurrent Neural Networks
This paper addresses the problem of pixel-level segmentation and classification of scene images with an entirely learning-based approach using Long Short Term Memory (LSTM) recurrent neural networks, which are commonly used for sequence classification.
