The emerging trends of multi-label learning

W Liu, H Wang, X Shen… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
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 …

Large loss matters in weakly supervised multi-label classification

Y Kim, JM Kim, Z Akata, J Lee - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
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 …

Learning a deep convnet for multi-label classification with partial labels

T Durand, N Mehrasa, G Mori - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
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 …

Cdul: Clip-driven unsupervised learning for multi-label image classification

R Abdelfattah, Q Guo, X Li, X Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Weakly supervised deep matrix factorization for social image understanding

Z Li, J Tang - IEEE Transactions on Image Processing, 2016 - ieeexplore.ieee.org
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 …

Structured semantic transfer for multi-label recognition with partial labels

T Chen, T Pu, H Wu, Y Xie, L Lin - … of the AAAI conference on artificial …, 2022 - ojs.aaai.org
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 …

Interactive multi-label cnn learning with partial labels

D Huynh, E Elhamifar - … of the IEEE/CVF Conference on …, 2020 - openaccess.thecvf.com
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 …

Bridging the gap between model explanations in partially annotated multi-label classification

Y Kim, JM Kim, J Jeong, C Schmid… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

Acknowledging the unknown for multi-label learning with single positive labels

D Zhou, P Chen, Q Wang, G Chen, PA Heng - European Conference on …, 2022 - Springer
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 …

Hashing with mutual information

F Cakir, K He, SA Bargal… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
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 …