Rethinking CNN models for audio classification
In this paper, we show that ImageNet-Pretrained standard deep CNN models can be used
as strong baseline networks for audio classification. Even though there is a significant�…
as strong baseline networks for audio classification. Even though there is a significant�…
Prior: Prototype representation joint learning from medical images and reports
Contrastive learning based vision-language joint pre-training has emerged as a successful
representation learning strategy. In this paper, we present a prototype representation�…
representation learning strategy. In this paper, we present a prototype representation�…
Exploring the limits of large scale pre-training
Recent developments in large-scale machine learning suggest that by scaling up data,
model size and training time properly, one might observe that improvements in pre-training�…
model size and training time properly, one might observe that improvements in pre-training�…
Deep facial diagnosis: deep transfer learning from face recognition to facial diagnosis
The relationship between face and disease has been discussed from thousands years ago,
which leads to the occurrence of facial diagnosis. The objective here is to explore the�…
which leads to the occurrence of facial diagnosis. The objective here is to explore the�…
[HTML][HTML] Review of the state of the art of deep learning for plant diseases: A broad analysis and discussion
Deep learning (DL) represents the golden era in the machine learning (ML) domain, and it
has gradually become the leading approach in many fields. It is currently playing a vital role�…
has gradually become the leading approach in many fields. It is currently playing a vital role�…
3d self-supervised methods for medical imaging
Self-supervised learning methods have witnessed a recent surge of interest after proving
successful in multiple application fields. In this work, we leverage these techniques, and we�…
successful in multiple application fields. In this work, we leverage these techniques, and we�…
How does learning rate decay help modern neural networks?
Learning rate decay (lrDecay) is a\emph {de facto} technique for training modern neural
networks. It starts with a large learning rate and then decays it multiple times. It is empirically�…
networks. It starts with a large learning rate and then decays it multiple times. It is empirically�…
Automatic severity classification of diabetic retinopathy based on densenet and convolutional block attention module
Diabetic Retinopathy (DR)-a complication developed due to heightened blood glucose
levels-is deemed one of the most sight-threatening diseases. Unfortunately, DR screening is�…
levels-is deemed one of the most sight-threatening diseases. Unfortunately, DR screening is�…
Natural synthetic anomalies for self-supervised anomaly detection and localization
We introduce a simple and intuitive self-supervision task, Natural Synthetic Anomalies
(NSA), for training an end-to-end model for anomaly detection and localization using only�…
(NSA), for training an end-to-end model for anomaly detection and localization using only�…
Dive into the details of self-supervised learning for medical image analysis
Self-supervised learning (SSL) has achieved remarkable performance in various medical
imaging tasks by dint of priors from massive unlabeled data. However, regarding a specific�…
imaging tasks by dint of priors from massive unlabeled data. However, regarding a specific�…