Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts (2020-08-03T00:00:00.000000Z)

TL;DR

Despite its simplicity, the proposed weakly supervised object detection method shows competitive results on a range of publicly available datasets, including paintings, watercolors, cliparts and comics and allows to quickly learn unseen visual categories.

Authors

Nicolas Gonthier

3 papers

Y. Gousseau

3 papers

Saïd Ladjal

2 papers

TL;DR

Authors

References88 items

A deeper look at vision and memory

Machine Learning for Cultural Heritage: A Survey

Deeply Aligned Adaptation for Cross-domain Object Detection

Visual Question Answering for Cultural Heritage

Webly-supervised zero-shot learning for artwork instance recognition

Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation

Linking Art through Human Poses

Micro-work, artificial intelligence and the automotive industry

The iMet Collection 2019 Challenge Dataset

C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection

Context-Aware Embeddings for Automatic Art Analysis

Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature Learning

Multitask Painting Categorization by Deep Multibranch Neural Network

Strong-Weak Distribution Alignment for Adaptive Object Detection

Artistic Object Recognition by Unsupervised Style Adaptation

ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

Dissimilarity Coefficient Based Weakly Supervised Object Detection

The Open Images Dataset V4

OmniArt

Weakly Supervised Object Detection in Artworks

Weakly Supervised Region Proposal Network and Object Detection

Deep Transfer Learning for Art Classification Problems

Adaptive Batch Normalization for practical domain adaptation

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

Min-Entropy Latent Model for Weakly Supervised Object Detection

W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection

Do Better ImageNet Models Transfer Better?

Zigzag Learning for Weakly Supervised Object Detection

New Techniques for the Digitization of Art Historical Photographic Archives - the Case of the Cini Foundation in Venice

Cross-Domain Weakly-Supervised Object Detection Through Progressive Domain Adaptation

The Shape of Art History in the Eyes of the Machine

Recognizing Art Style Automatically in Painting with Deep Learning

A Dual-Network Progressive Approach to Weakly Supervised Object Detection

DeepArt: Learning Joint Representations of Visual Arts

Deeper, Broader and Artier Domain Generalization

Soft Proposal Networks for Weakly Supervised Object Localization

Domain Transfer for Delving into Deep Networks Capacity to De-Abstract Art

BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography

Multiple Instance Detection Network with Online Instance Classifier Refinement

Weakly Supervised Learning of Deformable Part-Based Models for Object Detection via Region Proposals

Multiple instance learning: A survey of problem characteristics and applications

Weakly Supervised Cascaded Convolutional Networks

Revisiting multiple instance neural networks

Detecting People in Artwork with CNNs

Visual Link Retrieval in a Database of Paintings

ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization

The complexity model of communication with computer images

Weakly Supervised Object Localization with Progressive Domain Adaptation

Object recognition in art drawings: Transfer of a neural network

Learning scale-variant and scale-invariant features for deep image classification

Weakly Supervised Deep Detection Networks

Is object localization for free? - Weakly-supervised learning with convolutional neural networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Fast R-CNN

Cross-depiction problem: Recognition and synthesis of photographs and artwork

A theoretical and empirical analysis of support vector machine methods for multiple-instance classification

Edge Boxes: Locating Object Proposals from Edges

In Search of Art

ImageNet Large Scale Visual Recognition Challenge

Microsoft COCO: Common Objects in Context

On learning to localize objects with minimal supervision

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

Selective Search for Object Recognition

Crowdsourcing Annotations for Visual Object Detection

A convex relaxation for weakly supervised classifiers

Weakly supervised object detector learning with model drift detection

Adapting Visual Category Models to New Domains

Object Detection with Discriminatively Trained Part Based Models

Weakly supervised discriminative localization and classification: a joint learning process

Deterministic Annealing for Multiple-Instance Learning

The art of detection.

Solving the Multiple Instance Problem with Axis-Parallel Rectangles

On the complexity of polyhedral separability

The perceptron: a probabilistic model for information storage and organization in the brain.

Finding Visual Patterns in Artworks: An Interactive Search Engine to Detect Objects in Artistic Images

Online Collection Catalogue -Research