Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts

@article{Gonthier2021MultipleIL,
  title={Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts},
  author={Nicolas Gonthier and Sa{\"i}d Ladjal and Yann Gousseau},
  journal={ArXiv},
  year={2021},
  volume={abs/2008.01178}
}
Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a simple multiple instance approach applied on pre-trained deep features yields excellent performances on non-photographic datasets, possibly including new classes. The approach does not include any fine-tuning or cross-domain learning and is… 
Comparing CAM Algorithms for the Identification of Salient Image Features in Iconography Artwork Analysis
TLDR
This work compares state-of-the-art algorithms in terms of their capacity of identifying the iconographic attributes that determine the classification of characters in Christian art paintings to open the way to the automatic creation of bounding boxes for training detectors of iconographic symbols inChristian art images.
A Dataset and a Convolutional Model for Iconography Classification in Paintings
TLDR
A novel paintings data set for iconography classification is introduced and the quantitative and qualitative results of applying a Convolutional Neural Network (CNN) classifier to the recognition of the iconography of artworks are presented.
Improving Object Detection in Art Images Using Only Style Transfer
TLDR
A process for training neural networks to localize objects — specifically people — in art images to process art images is proposed and evaluated and a large dataset for training and validation is generated by modifying the images in the COCO dataset using AdaIn style transfer.
Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity
TLDR
Mixed supervision object detection with mixed supervision is considered, which learns novel object categories using weak annotations with the help of full annotations of existing base object categories, and further transfer mask prior and semantic similarity to bridge the gap between novel categories and base categories.
Vision-Aided Radio: User Identity Match in Radio and Video Domains Using Machine Learning
TLDR
This work compares the use of Deep Neural Network and Random Forest classifiers and shows that the former performed better across all experiments, achieving classification accuracy greater than 99%.

References

SHOWING 1-10 OF 110 REFERENCES
‘L’
  • P. Alam
  • Composites Engineering: An A–Z Guide
  • 2021
Soft Proposal Networks for Weakly Supervised Object Localization
TLDR
This paper designs a network component, Soft Proposal (SP), to be plugged into any standard convolutional architecture to introduce the nearly cost-free object proposal, orders of magnitude faster than state-of-the-art methods.
‘K’
  • P. Alam
  • Composites Engineering: An A–Z Guide
  • 2021
Min-Entropy Latent Model for Weakly Supervised Object Detection
TLDR
A min-entropy latent model (MELM) is proposed for weakly supervised object detection, unified with feature learning and optimized with a recurrent learning algorithm, which progressively transfers the weak supervision to object locations.
Neural Networks for Multi-Instance Learning
TLDR
A popular neural network algorithm is adapted for multi-instance learning through employing a specific error function and experiments show that the adapted algorithm achieves good result on the drug activity prediction data.
  • 2020
'I.
TLDR
Patients emphasised 'having more energy' when reporting improvements in their physical health following treatment and their desire to help other patients to receive treatment was connected to their experience of the services that they received and their perceived health outcomes.
Deeply Aligned Adaptation for Cross-domain Object Detection
TLDR
This work proposes an end-to-end solution based on Faster R-CNN, where ground-truth annotations are available for source images but not for target ones during training, and develops a foreground-background aware alignment module to further reduce the domain mismatch.
Machine Learning for Cultural Heritage: A Survey
TLDR
A critical look at the use of ML in CH and why CH has only limited adoption of ML is given, and the dominant divides within ML, Supervised, Semi-supervised and Unsupervised are analysed.
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection
TLDR
This paper first shows that instances can be assigned object or background labels directly based on proposal clusters for instance classifier refinement, and then shows that treating each cluster as a small new bag yields fewer ambiguities than the directly assigning label method.
...
1
2
3
4
5
...