Papers › Spatial Memory for Context Reasoning in Object Detection

Spatial Memory for Context Reasoning in Object Detection

13 Apr 2017ICCV 2017 10arXiv:1704.04224archive 2025-07-28

Xinlei Chen, Abhinav Gupta

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

35 repositories listed; official and paper-mentioned ones first.

endernewton/tf-faster-rcnn officialmentioned in papermentioned on GitHubtfMIT report
1512159/tf-faster-rcnn-medico mentioned on GitHubtf report
AlphaJia/tf-faster-rcnn mentioned on GitHubtf report
ChestnutLi/tf-faster-rcnn mentioned on GitHubtf report
Kenneth-Wong/tf-faster-rcnn mentioned on GitHubtf report
KyeongmoonKim/sb mentioned on GitHubtf report
PengchengAi/tf-faster-rcnn-pcai mentioned on GitHubtf report
achiyaj/vqa-sandbox mentioned on GitHubtf report
buaaYYC/faster-rcnn-tensorflow mentioned on GitHubtf report
csmiler/tf-faster-rcnn-cpu mentioned on GitHubtf report
daxiapazi/faster-rcnn mentioned on GitHubtf report
hj963434688/Faster_rcnn mentioned on GitHubtf report
huan123/py-fatser-rcnn mentioned on GitHubtf report
insigh/Faster-RCNN-Tensorflow mentioned on GitHubtf report
ithuanhuan/gpu-py3-faster-rcnn mentioned on GitHubtf report
ithuanhuan/py-fatser-rcnn mentioned on GitHubtf report
liuqiang3/faster_rcnn mentioned on GitHubtf report
mappy/tf-faster-rcnn mentioned on GitHubtf report
mengyingfei/faster-rcnn-tf mentioned on GitHubtf report
nautilus261/tf-faster-rcnn mentioned on GitHubtf report
neuqgz/modify-faster-rcnn-tf mentioned on GitHubtf report
piaosonglin1985/tf-faster-rcnn mentioned on GitHubtf report
shikorab/tf-faster-rcnn mentioned on GitHubtf report
tianhai123/tf-faster-rcnn mentioned on GitHubtf report
tigerofmurder/tf-faster-rcnn mentioned on GitHubtf report
vietlinhtspt/NewFasterRCNN mentioned on GitHubtf report
wangzpeng/tf-faster-rcnn mentioned on GitHubtf report
xinpingwang/tf-faster-rcnn mentioned on GitHubtf report
yzgrfsy/tf-fastrcnn-crop mentioned on GitHubtf report
zxqcreations/faster-rcnn-tf mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ObjectObject DetectionSpatial Reasoning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Memory Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections