Computational Baby Learning
Explore this paper's citation graph
Summary
A computational model for slightly-supervised object detection, based on prior knowledge modelling, exemplar learning and learning with video contexts, that can beat the state-of-the-art full-training based performances by learning from very few samples for each object category, along with about 20,000 unlabeled videos.
- Type
- preprint
- Published
- 2014-11-11
- Cited by
- 26
- References
- 40
- Access
- Open access
- OpenAlex
- https://openalex.org/W1659581753
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:15197739
Keywords
Pascal (unit), Computer science, Convolutional neural network, Artificial intelligence, Detector
References
- Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
- HCP: A Flexible CNN Framework for Multi-Label Image Classification
- Bottom-Up Segmentation for Top-Down Detection
- NEIL: Extracting Visual Knowledge from Web Data
- Regionlets for Generic Object Detection
- Learning object class detectors from weakly annotated video
- Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video
- Ensemble of exemplar-SVMs for object detection and beyond
- Enriching Visual Knowledge Bases via Object Discovery and Segmentation
- SUN database: Large-scale scene recognition from abbey to zoo
- Learning Hierarchical Features for Scene Labeling
- The Pascal Visual Object Classes (VOC) Challenge
- Associative Embeddings for Large-Scale Knowledge Transfer with Self-Assessment
- Scalable Object Detection Using Deep Neural Networks
- Semi-Supervised Self-Training of Object Detection Models
- Learning Everything about Anything: Webly-Supervised Visual Concept Learning
- Going deeper with convolutions
- Self-Paced Learning with Diversity
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Cited by
- Unsupervised Learning of Visual Representations Using Videos
- BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
- Learning to See by Moving
- Scale-Aware Fast R-CNN for Pedestrian Detection
- Understanding Blooming Human Groups in Social Networks
- Watch and learn: Semi-supervised learning of object detectors from videos
- Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images
- Object Detection Networks on Convolutional Feature Maps
- STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation
- Object Recognition Based on Amounts of Unlabeled Data
- Unsupervised Category Discovery via Looped Deep Pseudo-Task Optimization Using a Large Scale Radiology Image Database
- Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection
- Learning object models from few examples
- Self Paced Deep Learning for Weakly Supervised Object Detection
- Transferring deep representation for NIR-VIS heterogeneous face recognition
- Unsupervised Joint Mining of Deep Features and Image Labels for Large-Scale Radiology Image Categorization and Scene Recognition
- Local structured representation for generic object detection
- Improving multi-label classification using scene cues
- Discovering and Leveraging Visual Structure for Large-Scale Recognation
- Multimodal Co-Training for Selecting Good Examples from Webly Labeled Video
Related papers
- Application of Convolutional Neural Network for Image Classification on Pascal VOC Challenge 2012 dataset
- Deep Convolution Neural Network for RBC Images
- Leaf Features Extraction for Plant Classification using CNN
- Improved Regional Proposal Generation and Proposal Selection Method for Weakly Supervision Object detection
- Object detection using improved YOLOv3-tiny based on pyramid pooling
- Improving object detection via improving accuracy of object localization
- Deep CNN models for pulmonary nodule classification: Model modification, model integration, and transfer learning