Scaling Object Detection by Transferring Classification Weights

Abstract

Large scale object detection datasets are constantly increasing their size in terms of the number of classes and annotations count. Yet, the number of object-level categories annotated in detection datasets is an order of magnitude smaller than image-level classification labels. State-of-the art object detection models are trained in a supervised fashion and this limits the number of object classes they can detect. In this paper, we propose a novel weight transfer network (WTN) to effectively and efficiently transfer knowledge from classification network's weights to detection network's weights to allow detection of novel classes without box supervision. We first introduce input and feature normalization schemes to curb the under-fitting during training of a vanilla WTN. We then propose autoencoder-WTN (AE-WTN) which uses reconstruction loss to preserve classification network's information over all classes in the target latent space to ensure generalization to novel classes. Compared to vanilla WTN, AE-WTN obtains absolute performance gains of 6% on two Open Images evaluation sets with 500 seen and 57 novel classes respectively, and 25% on a Visual Genome evaluation set with 200 novel classes. The code is available at https://github.com/xternalz/AE-WTN.

arXiv commentICCV 2019

References in corpus (14)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Decoupled Weight Decay Regularization
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Opening the Black Box of Deep Neural Networks via Information
• Semi-Supervised Learning with Ladder Networks
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• LSDA: Large Scale Detection Through Adaptation
• Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification
• Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection
• Batch Normalization is a Cause of Adversarial Vulnerability
• Revisiting Activation Regularization for Language RNNs
• Scene Graph Generation with External Knowledge and Image Reconstruction
• PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track