Recognizing Novel Objects in Novel Surroundings with Single-shot Detectors

Tuesday, May 22, 4:10 PM - 4:40 PM
Summit Track: 
Technical Insights II
Room 203/204

Our 2016 work on single-shot object detection (SSD) reduced the computation cost for accurate detection of object categories to be in the same range as image classification, enabling deployment of general object detection at scale. Subsequent extensions add segmentation and improve accuracy, but still require many training examples in real-world contexts for each object category. In applications, it may be desirable to detect new objects or categories for which many training examples are not readily available. We consider two approaches to address this challenge. The first takes a small number of examples of objects not in context and composes them into scenes in order to construct training examples. The other approach learns to detect objects that are similar to a small number of target images provided during detection and does not requiring retraining the network for new targets.


Alexander C Berg

Associate Professor, UNC Chapel Hill

Dr. Berg works on computational visual recognition as an associate professor at UNC Chapel Hill and CTO of Shopagon Inc. His group co-founded and co-organized the ImageNet Large Scale Visual Recognition Challenge (ImageNet Challenge 2010-2017) and is currently co-organizing the Low-Power Image Recognition Challenge (2015-). The Berg group released the first Single Shot Detector (SSD) to beat two-stage object detectors in 2016 in addition to years of work on scaling up visual recognition, and connecting computer vision to natural language processing and robotics. Dr. Berg has won the Marr, Helmholtz and Everingham prizes.

See you at the Summit! May 20-23 in Santa Clara, California!
Register today and reserve your hotel room!