Related papers: Data Priming Network for Automatic Check-Out

The future large adaptive telescopes will trigger new constraints for the calibration of Adaptive Optics (AO) systems equipped with pre-focal Deformable Mirrors (DM). The image of the DM actuators grid as seen by the Wave-Front Sensor (WFS)…

Adversarial examples are considered a serious issue for safety critical applications of AI, such as finance, autonomous vehicle control and medicinal applications. Though significant work has resulted in increased robustness of systems to…

Data augmentation (DA) enhances model generalization in computer vision but may introduce biases, impacting class accuracy unevenly. Our study extends this inquiry, examining DA's class-specific bias across various datasets, including those…

The poultry industry has been driven by broiler chicken production and has grown into the world's largest animal protein sector. Automated detection of chicken carcasses on processing lines is vital for quality control, food safety, and…

The removal of carefully-selected examples from training data has recently emerged as an effective way of improving the robustness of machine learning models. However, the best way to select these examples remains an open question. In this…

Deep learning vision systems are widely deployed across applications where reliability is critical. However, even today's best models can fail to recognize an object when its pose, lighting, or background varies. While existing benchmarks…

Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent years. While lots of network architectures have been…

Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings, in which the…

The major challenge in today's computer vision scenario is the availability of good quality labeled data. In a field of study like image classification, where data is of utmost importance, we need to find more reliable methods which can…

Successful visual navigation depends upon capturing images that contain sufficient useful information. In this letter, we explore a data-driven approach to account for environmental lighting changes, improving the quality of images for use…

Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection. However, learning highly accurate models relies on…

Pre-training (PT) followed by fine-tuning (FT) is an effective method for training neural networks, and has led to significant performance improvements in many domains. PT can incorporate various design choices such as task and data…

Both appearance cue and constraint cue are vital for human pose estimation. However, there is a tendency in most existing works to overfitting the former and overlook the latter. In this paper, we propose Augmentation by Information…

The deep learning technique has been shown to be effectively addressed several image analysis tasks in the computer-aided diagnosis scheme for mammography. The training of an efficacious deep learning model requires large data with diverse…

We propose a novel data augmentation method named 'FenceMask' that exhibits outstanding performance in various computer vision tasks. It is based on the 'simulation of object occlusion' strategy, which aim to achieve the balance between…

Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i.e., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled target-domain data.…

While fine-grained object recognition is an important problem in computer vision, current models are unlikely to accurately classify objects in the wild. These fully supervised models need additional annotated images to classify objects in…

Detection in large-scale scenes is a challenging problem due to small objects and extreme scale variation. It is essential to focus on the image regions of small objects. In this paper, we propose a novel Adaptive Zoom (AdaZoom) network as…

Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zero-shot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of prompt learning, where…

Preserving privacy is a growing concern in our society where sensors and cameras are ubiquitous. In this work, for the first time, we propose a trainable image acquisition method that removes the sensitive identity revealing information in…