Related papers: Unlocking ImageNet's Multi-Object Nature: Automate…
Annotated images are required for both supervised model training and evaluation in image classification. Manually annotating images is arduous and expensive, especially for multi-labeled images. A recent trend for conducting such laboursome…
Large-scale multi-label classification datasets are commonly, and perhaps inevitably, partially annotated. That is, only a small subset of labels are annotated per sample. Different methods for handling the missing labels induce different…
A commonly accepted hypothesis is that models with higher accuracy on Imagenet perform better on other downstream tasks, leading to much research dedicated to optimizing Imagenet accuracy. Recently this hypothesis has been challenged by…
Multi-label classification is an approach which allows a datapoint to be labelled with more than one class at the same time. A common but trivial approach is to train individual binary classifiers per label, but the performance can be…
Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the…
Successfully training a deep neural network demands a huge corpus of labeled data. However, each label only provides limited information to learn from and collecting the requisite number of labels involves massive human effort. In this…
Supervised classification algorithms are used to solve a growing number of real-life problems around the globe. Their performance is strictly connected with the quality of labels used in training. Unfortunately, acquiring good-quality…
Auto-annotation by ensemble of models is an efficient method of learning on unlabeled data. Wrong or inaccurate annotations generated by the ensemble may lead to performance degradation of the trained model. To deal with this problem we…
The task of multi-label image classification is to recognize all the object labels presented in an image. Though advancing for years, small objects, similar objects and objects with high conditional probability are still the main…
Supervised learning typically focuses on learning transferable representations from training examples annotated by humans. While rich annotations (like soft labels) carry more information than sparse annotations (like hard labels), they are…
Object counting aims to estimate the number of objects in images. The leading counting approaches focus on the single category counting task and achieve impressive performance. Note that there are multiple categories of objects in real…
Multi-object tracking has seen a lot of progress recently, albeit with substantial annotation costs for developing better and larger labeled datasets. In this work, we remove the need for annotated datasets by proposing an unsupervised…
Building rich machine learning datasets in a scalable manner often necessitates a crowd-sourced data collection pipeline. In this work, we use human studies to investigate the consequences of employing such a pipeline, focusing on the…
Joint representation of geometry, colour and semantics using a 3D neural field enables accurate dense labelling from ultra-sparse interactions as a user reconstructs a scene in real-time using a handheld RGB-D sensor. Our iLabel system…
Disaggregated performance metrics across demographic groups are a hallmark of fairness assessments in computer vision. These metrics successfully incentivized performance improvements on person-centric tasks such as face analysis and are…
Learning an object detector or retrieval requires a large data set with manual annotations. Such data sets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose to exploit…
Although unsupervised person re-identification (RE-ID) has drawn increasing research attentions due to its potential to address the scalability problem of supervised RE-ID models, it is very challenging to learn discriminative information…
Image labeling is a critical bottleneck in the development of computer vision technologies, often constraining machine learning performance due to the time-intensive nature of manual annotations. This work introduces a novel approach that…
With the rapid adoption of multimodal large language models (MLLMs) across diverse applications, there is a pressing need for task-centered, high-quality training data. A key limitation of current training datasets is their reliance on…
Multi-label learning has attracted significant interests in computer vision recently, finding applications in many vision tasks such as multiple object recognition and automatic image annotation. Associating multiple labels to a complex…