Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features
This addresses the problem of open-vocabulary multi-label classification for computer vision applications, offering incremental improvements through novel components like Pyramid-Forwarding and Selective Language Supervision.
The paper tackles the challenge of classifying previously unseen labels in multi-label recognition by proposing ADDS, a novel algorithm with a Dual-Modal decoder and alignment between visual and textual features, achieving state-of-the-art performance on benchmarks like NUS-WIDE, ImageNet-1k, ImageNet-21k, and MS-COCO.
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).