Papers › Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned...
Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features
Shichao Xu, Yikang Li, Jenhao Hsiao, Chiuman Ho, Zhu Qi
In computer vision, multi-label recognition are important tasks with many real-world applications, but classifying previously unseen labels remains a significant challenge. In this paper, we propose a novel algorithm, Aligned Dual moDality ClaSsifier (ADDS), which includes a Dual-Modal decoder (DM-decoder) with alignment between visual and textual features, for open-vocabulary multi-label classification tasks. Then we design a simple and yet effective method called Pyramid-Forwarding to enhance the performance for inputs with high resolutions. Moreover, the Selective Language Supervision is applied to further enhance the model performance. Extensive experiments conducted on several standard benchmarks, NUS-WIDE, ImageNet-1k, ImageNet-21k, and MS-COCO, demonstrate that our approach significantly outperforms previous methods and provides state-of-the-art performance for open-vocabulary multi-label classification, conventional multi-label classification and an extreme case called single-to-multi label classification where models trained on single-label datasets (ImageNet-1k, ImageNet-21k) are tested on multi-label ones (MS-COCO and NUS-WIDE).
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Multi-Label Classification | MS-COCO | ADDS(ViT-L-336, resolution 1344) | mAP | 93.54 | #1 of 34 | Archive leaderboard | report |
| Multi-Label Classification | MS-COCO | ADDS(ViT-L-336, resolution 640) | mAP | 93.41 | #2 of 34 | Archive leaderboard | report |
| Multi-Label Classification | MS-COCO | ADDS(ViT-L-336, resolution 336) | mAP | 91.76 | #3 of 34 | Archive leaderboard | report |
| Multi-label zero-shot learning | ImageNet-1k to MSCOCO | ADDS | mAP | 67.10 | #1 of 1 | Archive leaderboard | report |
| Multi-label zero-shot learning | NUS-WIDE | ADDS (ViT-L-336, resolution 336) | mAP | 39.01 | #2 of 10 | Archive leaderboard | report |
| Multi-label zero-shot learning | NUS-WIDE | ADDS (ViT-B-32, resolution 224) | mAP | 36.56 | #4 of 10 | 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