Papers › MlTr: Multi-label Classification with Transformer

MlTr: Multi-label Classification with Transformer

11 Jun 2021arXiv:2106.06195archive 2025-07-28

Xing Cheng, Hezheng Lin, Xiangyu Wu, Fan Yang, Dong Shen, Zhongyuan Wang, Nian Shi, Honglin Liu

The task of multi-label image classification is to recognize all the object labels presented in an image. Though advancing for years, small objects, similar objects and objects with high conditional probability are still the main bottlenecks of previous convolutional neural network(CNN) based models, limited by convolutional kernels' representational capacity. Recent vision transformer networks utilize the self-attention mechanism to extract the feature of pixel granularity, which expresses richer local semantic information, while is insufficient for mining global spatial dependence. In this paper, we point out the three crucial problems that CNN-based methods encounter and explore the possibility of conducting specific transformer modules to settle them. We put forward a Multi-label Transformer architecture(MlTr) constructed with windows partitioning, in-window pixel attention, cross-window attention, particularly improving the performance of multi-label image classification tasks. The proposed MlTr shows state-of-the-art results on various prevalent multi-label datasets such as MS-COCO, Pascal-VOC, and NUS-WIDE with 88.5%, 95.8%, and 65.5% respectively. The code will be available soon at https://github.com/starmemda/MlTr/

PaperPDFCode

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

Code

starmemda/MlTr officialmentioned in papermentioned on GitHub 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

ClassificationImage ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationMulti-Label Image Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Classification MS-COCO MlTr-XL(ImageNet-21K pretraining, resolution 384) mAP 90.0 #12 of 34 Archive leaderboard report
Multi-Label Classification MS-COCO MlTr-L(ImageNet-21K pretraining, resolution 384) mAP 88.5 #14 of 34 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerVision Transformer

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