Related papers: Unlocking ImageNet's Multi-Object Nature: Automate…

Due to the nature of enhancement--the absence of paired ground-truth information, high-level vision tasks have been recently employed to evaluate the performance of low-light image enhancement. A widely-used manner is to see how accurately…

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 work discusses the use of machine learning algorithms for anomaly detection in medical image analysis and how the performance of these algorithms depends on the number of annotators and the quality of labels. To address the issue of…

Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of…

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…

The success of medical image segmentation usually requires a large number of high-quality labels. But since the labeling process is usually affected by the raters' varying skill levels and characteristics, the estimated masks provided by…

Multi-label learning deals with the classification problems where each instance can be assigned with multiple labels simultaneously. Conventional multi-label learning approaches mainly focus on exploiting label correlations. It is usually…

Label noise remains a challenge for training robust classification models. Most methods for mitigating label noise have been benchmarked using primarily datasets with synthetic noise. While the need for datasets with realistic noise…

We introduce Fluid Annotation, an intuitive human-machine collaboration interface for annotating the class label and outline of every object and background region in an image. Fluid annotation is based on three principles: (I) Strong…

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…

Obtaining annotations for complex computer vision tasks such as object detection is an expensive and time-intense endeavor involving a large number of human workers or expert opinions. Reducing the amount of annotations required while…

After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…

Current deep learning paradigms largely benefit from the tremendous amount of annotated data. However, the quality of the annotations often varies among labelers. Multi-observer studies have been conducted to study these annotation…

Learned object detection methods based on fusion of LiDAR and camera data require labeled training samples, but niche applications, such as warehouse robotics or automated infrastructure, require semantic classes not available in large…

In reality, learning from multi-view multi-label data inevitably confronts three challenges: missing labels, incomplete views, and non-aligned views. Existing methods mainly concern the first two and commonly need multiple assumptions to…

Image classification benchmark datasets such as CIFAR, MNIST, and ImageNet serve as critical tools for model evaluation. However, despite the cleaning efforts, these datasets still suffer from pervasive noisy labels and often contain…

Multi-label learning handles instances associated with multiple class labels. The original label space is a logical matrix with entries from the Boolean domain $\in \left \{ 0,1 \right \}$. Logical labels are not able to show the relative…

Deep neural networks have been shown to easily overfit to biased training data with label noise or class imbalance. Meta-learning algorithms are commonly designed to alleviate this issue in the form of sample reweighting, by learning a meta…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…

Multi-instance multi-label (MIML) learning is widely applicated in numerous domains, such as the image classification where one image contains multiple instances correlated with multiple logic labels simultaneously. The related labels in…