Related papers: DeepFirearm: Learning Discriminative Feature Repre…

We propose a random convolutional neural network to generate a feature space in which we study image classification and retrieval performance. Put briefly we apply random convolutional blocks followed by global average pooling to generate a…

Pursuing realistic results according to human visual perception is the central concern in the image transformation tasks. Perceptual learning approaches like perceptual loss are empirically powerful for such tasks but they usually rely on…

Few-shot learning has emerged as a powerful paradigm for training models with limited labeled data, addressing challenges in scenarios where large-scale annotation is impractical. While extensive research has been conducted in the image…

Images with different resolutions are ubiquitous in public person re-identification (ReID) datasets and real-world scenes, it is thus crucial for a person ReID model to handle the image resolution variations for improving its generalization…

Recently, the contrastive learning paradigm has achieved remarkable success in high-level tasks such as classification, detection, and segmentation. However, contrastive learning applied in low-level tasks, like image restoration, is…

This study aims to optimize the few-shot image classification task and improve the model's feature extraction and classification performance by combining self-supervised learning with the deep network model ResNet-101. During the training…

Historical watermark recognition is a highly practical, yet unsolved challenge for archivists and historians. With a large number of well-defined classes, cluttered and noisy samples, different types of representations, both subtle…

Single Image Super-Resolution (SISR) task refers to learn a mapping from low-resolution images to the corresponding high-resolution ones. This task is known to be extremely difficult since it is an ill-posed problem. Recently, Convolutional…

Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…

Plane Wave imaging enables many applications that require high frame rates, including localisation microscopy, shear wave elastography, and ultra-sensitive Doppler. To alleviate the degradation of image quality with respect to conventional…

Modern deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns, limiting their commercial use. Recent works suggest synthetic data as an alternative,…

One of the major challenges in training deep neural networks for text-to-image generation is the significant linguistic discrepancy between ground-truth captions of each image in most popular datasets. The large difference in the choice of…

The pursuit of learning robust representations without human supervision is a longstanding challenge. The recent advancements in self-supervised contrastive learning approaches have demonstrated high performance across various…

Fine-grained text to image synthesis involves generating images from texts that belong to different categories. In contrast to general text to image synthesis, in fine-grained synthesis there is high similarity between images of different…

In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requirement, Convolutional…

We propose a framework for the automatic one-shot segmentation of synthetic images generated by a StyleGAN. Our framework is based on the observation that the multi-scale hidden features in the GAN generator hold useful semantic information…

Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate the retrieval of overlapping images in 3D reconstruction. In…

Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the data augmentation strategy applied to generate positive…

Real-world data often have a long-tailed distribution, where the number of samples per class is not equal over training classes. The imbalanced data form a biased feature space, which deteriorates the performance of the recognition model.…

CLIP (Contrastive Language-Image Pre-training) uses contrastive learning from noise image-text pairs to excel at recognizing a wide array of candidates, yet its focus on broad associations hinders the precision in distinguishing subtle…