Related papers: CutMix: Regularization Strategy to Train Strong Cl…
Deep Convolutional Neural Networks have made an incredible progress in many Computer Vision tasks. This progress, however, often relies on the availability of large amounts of the training data, required to prevent over-fitting, which in…
Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is…
Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous methods inspired by dropout, which enhances generalization by…
While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network calibration, despite its importance. Neural collapse, a phenomenon where last-layer features…
Data augmentation reduces the generalization error by forcing a model to learn invariant representations given different transformations of the input image. In computer vision, on top of the standard image processing functions, data…
In this paper, we propose a novel convolutional neural network (CNN) architecture considering both local and global features for image enhancement. Most conventional image enhancement methods, including Retinex-based methods, cannot restore…
Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors.…
In semantic segmentation, the creation of pixel-level labels for training data incurs significant costs. To address this problem, semi-supervised learning, which utilizes a small number of labeled images alongside unlabeled images to…
Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation. Reliability encompasses robustness, predictive uncertainty and reduced bias. To improve reliability, we introduce…
The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for…
Dropout Regularization, serving to reduce variance, is nearly ubiquitous in Deep Learning models. We explore the relationship between the dropout rate and model complexity by training 2,000 neural networks configured with random…
In active learning, the focus is mainly on the selection strategy of unlabeled data for enhancing the generalization capability of the next learning cycle. For this, various uncertainty measurement methods have been proposed. On the other…
Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit…
Handling the ever-increasing scale of contemporary deep learning and transformer-based models poses a significant challenge. Overparameterized Transformer networks outperform prior art in Natural Language processing and Computer Vision.…
A novel approach of data augmentation based on irregular superpixel decomposition is proposed. This approach called SuperpixelGridMasks permits to extend original image datasets that are required by training stages of machine…
Recent advances in large-scale text-to-image diffusion models (e.g., FLUX.1) have greatly improved visual fidelity in consistent character generation and editing. However, existing methods rarely unify these tasks within a single framework.…
Few-shot hyperspectral image classification aims to identify the classes of each pixel in the images by only marking few of these pixels. And in order to obtain the spatial-spectral joint features of each pixel, the fixed-size patches…
For safety-critical applications such as autonomous driving, CNNs have to be robust with respect to unavoidable image corruptions, such as image noise. While previous works addressed the task of robust prediction in the context of…
We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach…
When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain. If the target domain covers a smaller visual…