Exabytes of data are generated daily by humans, leading to the growing needs for new
efforts in dealing with the grand challenges for multi-label learning brought by big data. For …

Weakly supervised multi-label classification (WSML) task, which is to learn a multi-label
classification using partially observed labels per image, is becoming increasingly important …

Deep ConvNets have shown great performance for single-label image classification (eg
ImageNet), but it is necessary to move beyond the single-label classification task because …

This paper presents a CLIP-based unsupervised learning method for annotation-free multi-
label image classification, including three stages: initialization, training, and inference. At the …

The number of images associated with weakly supervised user-provided tags has increased
dramatically in recent years. User-provided tags are incomplete, subjective and noisy. In this …

Multi-label image recognition is a fundamental yet practical task because real-world images
inherently possess multiple semantic labels. However, it is difficult to collect large-scale multi …

We address the problem of efficient end-to-end learning a multi-label Convolutional Neural
Network (CNN) on training images with partial labels. Training a CNN with partial labels …

Due to the expensive costs of collecting labels in multi-label classification datasets, partially
annotated multi-label classification has become an emerging field in computer vision. One …

Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets
often contain partial labels. We consider an extreme of this weakly supervised learning …

Binary vector embeddings enable fast nearest neighbor retrieval in large databases of high-
dimensional objects, and play an important role in many practical applications, such as …