Related papers: Developing efficient transfer learning strategies …

Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing…

While few-shot learning as a transfer learning paradigm has gained significant traction for scenarios with limited data, it has primarily been explored in the context of building unimodal and unilingual models. Furthermore, a significant…

The uprising trend of deep learning in computer vision and artificial intelligence can simply not be ignored. On the most diverse tasks, from recognition and detection to segmentation, deep learning is able to obtain state-of-the-art…

The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data. Recent research has found that neural style transfer algorithms can apply the artistic style of one image to another…

Building accurate models for rare skin diseases remains challenging due to the lack of sufficient labeled data and the inherently long-tailed distribution of available samples. These issues are further complicated by inconsistencies in how…

Facial landmark detection is a widely researched field of deep learning as this has a wide range of applications in many fields. These key points are distinguishing characteristic points on the face, such as the eyes center, the eye's inner…

Deep learning has shown substantial progress in image analysis. However, the computational demands of large, fully trained models remain a consideration. Transfer learning offers a strategy for adapting pre-trained models to new tasks.…

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…

Transfer learning is the predominant paradigm for training deep networks on small target datasets. Models are typically pretrained on large ``upstream'' datasets for classification, as such labels are easy to collect, and then finetuned on…

Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2. Scene categories are often defined by multi-level…

Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However the offline training is time-consuming and the learned generic representation may be less…

Advancing Machine Learning (ML)-based perception models for autonomous systems necessitates addressing weak spots within the models, particularly in challenging Operational Design Domains (ODDs). These are environmental operating conditions…

Existing transfer learning-based beam prediction approaches primarily rely on simple fine-tuning. When there is a significant difference in data distribution between the target domain and the source domain, simple fine-tuning limits the…

Traffic scene recognition, which requires various visual classification tasks, is a critical ingredient in autonomous vehicles. However, most existing approaches treat each relevant task independently from one another, never considering the…

Transfer learning from huge natural image datasets, fine-tuning of deep neural networks and the use of the corresponding pre-trained networks have become de facto the core of art analysis applications. Nevertheless, the effects of transfer…

Scene recognition is one of the basic problems in computer vision research with extensive applications in robotics. When available, depth images provide helpful geometric cues that complement the RGB texture information and help to identify…

Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based…

Medical image classification plays an increasingly vital role in identifying various diseases by classifying medical images, such as X-rays, MRIs and CT scans, into different categories based on their features. In recent years, deep…

Large pre-trained vision models achieve impressive success in computer vision. However, fully fine-tuning large models for downstream tasks, particularly in video understanding, can be prohibitively computationally expensive. Recent studies…

Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the…