Spatial Memory for Context Reasoning in Object Detection
arXiv:1704.04224
Abstract
Modeling instance-level context and object-object relationships is extremely challenging. It requires reasoning about bounding boxes of different classes, locations \etc. Above all, instance-level spatial reasoning inherently requires modeling conditional distributions on previous detections. Unfortunately, our current object detection systems do not have any {\bf memory} to remember what to condition on! The state-of-the-art object detectors still detect all object in parallel followed by non-maximal suppression (NMS). While memory has been used for tasks such as captioning, they mostly use image-level memory cells without capturing the spatial layout. On the other hand, modeling object-object relationships requires {\bf spatial} reasoning -- not only do we need a memory to store the spatial layout, but also a effective reasoning module to extract spatial patterns. This paper presents a conceptually simple yet powerful solution -- Spatial Memory Network (SMN), to model the instance-level context efficiently and effectively. Our spatial memory essentially assembles object instances back into a pseudo "image" representation that is easy to be fed into another ConvNet for object-object context reasoning. This leads to a new sequential reasoning architecture where image and memory are processed in parallel to obtain detections which update the memory again. We show our SMN direction is promising as it provides 2.2\% improvement over baseline Faster RCNN on the COCO dataset so far.
Draft submitted to ICCV 2017
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
- Feature Pyramid Networks for Object Detection
- Beyond Skip Connections: Top-Down Modulation for Object Detection
- Show and Tell: A Neural Image Caption Generator
- An Implementation of Faster RCNN with Study for Region Sampling
- Neural Map: Structured Memory for Deep Reinforcement Learning
- Hierarchical Object Detection with Deep Reinforcement Learning
- Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection
- End-to-end training of object class detectors for mean average precision