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 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 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 View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

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

endernewton/tf-faster-rcnn officialmentioned in papermentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Cross-Domain Object Detection Using Unsupervised Image Translation (arXiv:2601.11779; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
1512159/tf-faster-rcnn-medico mentioned on GitHubtfSyntology: not harvested report
AlphaJia/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
ChestnutLi/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
Kenneth-Wong/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
KyeongmoonKim/sb mentioned on GitHubtfSyntology: not harvested report
PengchengAi/tf-faster-rcnn-pcai mentioned on GitHubtfSyntology: not harvested report
PythonZhengbinChen/tf-faster-rcnn-cpu mentioned on GitHubtfSyntology: not harvested report
achiyaj/vqa-sandbox mentioned on GitHubtfSyntology: not harvested report
bareblackfoot/faster-rcnn.selection mentioned on GitHubtfSyntology: not harvested report
bareblackfoot/lddp-tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
buaaYYC/faster-rcnn-tensorflow mentioned on GitHubtfSyntology: not harvested report
csmiler/tf-faster-rcnn-cpu mentioned on GitHubtfSyntology: not harvested report
daxiapazi/faster-rcnn mentioned on GitHubtfSyntology: not harvested report
hj963434688/Faster_rcnn mentioned on GitHubtfSyntology: not harvested report
huan123/py-fatser-rcnn mentioned on GitHubtfSyntology: not harvested report
insigh/Faster-RCNN-Tensorflow mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
ithuanhuan/gpu-py3-faster-rcnn mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (arXiv:1506.01497; that paper's own run record: 79 ran (of which 9 constructed an object rather than computing a result; 47 with no instrument failure: 18 honoured, 5 violated, 24 with no contract checked; 32 where Syntology's instrument failed) · 45 unverified); nothing checks that they implement this paper's method. report
ithuanhuan/py-fatser-rcnn mentioned on GitHubtfSyntology: not harvested report
liuqiang3/faster_rcnn mentioned on GitHubtfSyntology: not harvested report
mappy/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
mengyingfei/faster-rcnn-tf mentioned on GitHubtfSyntology: not harvested report
nautilus261/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
neuqgz/modify-faster-rcnn-tf mentioned on GitHubtfSyntology: not harvested report
piaosonglin1985/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
rickyHong/faster-rcnn-tensorflow-repl mentioned on GitHubtfSyntology: not harvested report
shikorab/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
tianhai123/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
tigerofmurder/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
vietlinhtspt/NewFasterRCNN mentioned on GitHubtfSyntology: not harvested report
wangzpeng/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
wennieWN/endernewton_tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
xinpingwang/tf-faster-rcnn mentioned on GitHubtfSyntology: not harvested report
yzgrfsy/tf-fastrcnn-crop mentioned on GitHubtfSyntology: not harvested report
zxqcreations/faster-rcnn-tf mentioned on GitHubtfSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

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