Model recommendation: Generating object detectors from few samples

By Yu-Xiong Wang, Martial Hebert. 2015

48 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Growing a Brain: Fine-Tuning by Increasing Model Capacity (2017, background): “g that adaptation of old units is crucial for high performance. Transfer learning is related to both multi-task learning [32, 4, 28, 10, 11, 45, 24, 2] and learning novel categories from few examples [49, 19, 21, 35, 51, 22, 5, 13, 50, 47, 31]. Past techniques have applied such approaches to transfe”
Open-Vocabulary Object Detection Using Captions (2020, methodology): “However, most existing methods need bounding box annotations for all classes, and use weak supervision only as auxiliary data [14, 31, 40].”
Few-Shot Object Detection via Feature Reweighting (2018, background): “Few example object detection [25, 41, 8] assumes only a few labeled bounding boxes per class, but relies on abundant unlabeled images to generate trustworthy pseudo annotations for training.”
Watch and learn: Semi-supervised learning of object detectors from videos (2015, methodology): “For each labeled bounding box in Li, we compute a detection signature [24, 38, 54] using our exemplar detectors.”
Meta-Learning to Detect Rare Objects (2019, background): “There are other settings of detection with limited supervision, such as weakly-supervised detection [59, 5, 11], semi-supervised detection [69, 39, 12], and zero-shot detection [2, 41, 73], which are different from ours.”
Learning to Learn: Model Regression Networks for Easy Small Sample Learning (2016, background): “More crucially, current recognition systems assume a set of categories known a priori, despite the obviously dynamic and open nature of the visual world [12, 96, 64, 32].”
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild (2020, background): “Semi-supervised detection [50], [51], [52] makes use of a small amount of labeled images per class to generate pseudo labels on a large amount of unlabeled images for training.”
Learning to Model the Tail (2017, background): “The most related formulation is that of one/few-shot learning [43, 44, 45, 46, 47, 48, 21, 49, 35, 50, 23, 51, 52, 53, 54, 55, 56].”
Learning from Small Sample Sets by Combining Unsupervised Meta-Training with CNNs (2016, background): “In practice, however, for novel categories/tasks of interest, collecting a large corpus of annotated data to train CNNs from scratch is typically unrealistic, such as in robotics applications [4] and for customized categories [5].”
DOCK: Detecting Objects by Transferring Common-Sense Knowledge (2018, background): “Existing transfer learning approaches can be roughly divided into two groups: one that learns using bounding box annotations for both source and target categories [36,3,21,11,43,40], and another that learns using bounding box annotations for source categories but only image-level annotations for tar”