Related papers: Are we done with ImageNet?
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…
Recent fine-tuning techniques for diffusion models enable them to reproduce specific image sets, such as particular faces or artistic styles, but also introduce copyright and security risks. Dataset watermarking has been proposed to ensure…
One-hot labels do not represent soft decision boundaries among concepts, and hence, models trained on them are prone to overfitting. Using soft labels as targets provide regularization, but different soft labels might be optimal at…
This paper deals with the prediction of the memorability of a given image. We start by proposing an algorithm that reaches human-level performance on the LaMem dataset - the only large scale benchmark for memorability prediction. The…
Though anomaly detection (AD) can be viewed as a classification problem (nominal vs. anomalous) it is usually treated in an unsupervised manner since one typically does not have access to, or it is infeasible to utilize, a dataset that…
Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this…
We propose a novel approach to improve a visual-semantic embedding model by incorporating concept representations captured from an external structured knowledge base. We investigate its performance on image classification under both…
Deep learning algorithms have pushed the boundaries of computer vision research and have depicted commendable performance in a variety of applications. However, training a robust deep neural network necessitates a large amount of labeled…
Improving label quality in medical image segmentation is costly, but its benefits remain unclear. We systematically evaluate its impact using multiple pseudo-labeled versions of CT datasets, generated by models like nnU-Net,…
This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accurate label of each sample, our setting requires the model to…
The ImageNet dataset ushered in a flood of academic and industry interest in deep learning for computer vision applications. Despite its significant impact, there has not been a comprehensive investigation into the demographic attributes of…
Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition datasets. One of the primary issues stems from the semantic gap problem, which results in complex many-to-many mappings between…
Recently, a variety of regularization techniques have been widely applied in deep neural networks, such as dropout, batch normalization, data augmentation, and so on. These methods mainly focus on the regularization of weight parameters to…
High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to obtain and often affected by noise due to the labor-intensive and time-consuming nature of…
Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, employing experts to…
Repositories of images with semantic and emotion content descriptions are valuable tools in many areas such as Affective Computing and Human-Computer Interaction, but they are also important in the development of multimodal searchable…
Image annotation aims to annotate a given image with a variable number of class labels corresponding to diverse visual concepts. In this paper, we address two main issues in large-scale image annotation: 1) how to learn a rich feature…
In visual interactive labeling, users iteratively assign labels to data items until the machine model reaches an acceptable accuracy. A crucial step of this process is to inspect the model's accuracy and decide whether it is necessary to…
In this paper we address issues with image retrieval benchmarking on standard and popular Oxford 5k and Paris 6k datasets. In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation…
Image captioning models are becoming increasingly successful at describing the content of images in restricted domains. However, if these models are to function in the wild - for example, as assistants for people with impaired vision - a…