Papers › Large-Scale Long-Tailed Recognition in an Open World

Large-Scale Long-Tailed Recognition in an Open World

10 Apr 2019CVPR 2019 6arXiv:1904.05160archive 2025-07-28

Ziwei Liu, Zhongqi Miao, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu

Real world data often have a long-tailed and open-ended distribution. A practical recognition system must classify among majority and minority classes, generalize from a few known instances, and acknowledge novelty upon a never seen instance. We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes. OLTR must handle imbalanced classification, few-shot learning, and open-set recognition in one integrated algorithm, whereas existing classification approaches focus only on one aspect and deliver poorly over the entire class spectrum. The key challenges are how to share visual knowledge between head and tail classes and how to reduce confusion between tail and open classes. We develop an integrated OLTR algorithm that maps an image to a feature space such that visual concepts can easily relate to each other based on a learned metric that respects the closed-world classification while acknowledging the novelty of the open world. Our so-called dynamic meta-embedding combines a direct image feature and an associated memory feature, with the feature norm indicating the familiarity to known classes. On three large-scale OLTR datasets we curate from object-centric ImageNet, scene-centric Places, and face-centric MS1M data, our method consistently outperforms the state-of-the-art. Our code, datasets, and models enable future OLTR research and are publicly available at https://liuziwei7.github.io/projects/LongTail.html.

Paper PDF Conference PDF Code

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

Code

silicx/dlsa mentioned on GitHubpytorch report

zhmiao/OpenLongTailRecognition-OLTR mentioned on GitHubpytorchBSD-3-Clause 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

Classification Few-Shot Learning General Classification Long-tail Learning Long-tail learning with class descriptors Open Set Learning imbalanced classification

Datasets

Introduced by this paper, per the archive.

ImageNet-LT Places-LT

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Long-tail Learning	COCO-MLT	OLTR(ResNet-50)	Average mAP	45.83	#11 of 13	Archive leaderboard	report
Long-tail Learning	ImageNet-LT	OLTR	Top-1 Accuracy	35.6	#67 of 69	Archive leaderboard	report
Long-tail Learning	Places-LT	OLTR	Top-1 Accuracy	34.1	#28 of 29	Archive leaderboard	report
Long-tail Learning	VOC-MLT	OLTR(ResNet-50)	Average mAP	71.02	#11 of 13	Archive leaderboard	report
Long-tail learning with class descriptors	ImageNet-LT-d	OLTR	Per-Class Accuracy	37.7	#5 of 5	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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