Target Driven Instance Detection
arXiv:1803.04610
Abstract
While state-of-the-art general object detectors are getting better and better, there are not many systems specifically designed to take advantage of the instance detection problem. For many applications, such as household robotics, a system may need to recognize a few very specific instances at a time. Speed can be critical in these applications, as can the need to recognize previously unseen instances. We introduce a Target Driven Instance Detector(TDID), which modifies existing general object detectors for the instance recognition setting. TDID not only improves performance on instances seen during training, with a fast runtime, but is also able to generalize to detect novel instances.
References in corpus (6)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- High-Speed Tracking with Kernelized Correlation Filters
- Caffe: Convolutional Architecture for Fast Feature Embedding
- DSSD : Deconvolutional Single Shot Detector
- Beyond Skip Connections: Top-Down Modulation for Object Detection
Cited by in corpus (5)
- POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments
- OSSID: Online Self-Supervised Instance Detection by (and for) Pose Estimation
- Unsupervised Active Visual Search with Monte Carlo planning under Uncertain Detections
- Combining Deep Learning and Verification for Precise Object Instance Detection
- An Analysis of Object Representations in Deep Visual Trackers