Transformers have demonstrated tremendous success not only in the natural
language processing (NLP) domain but also the field of computer vision,
igniting various creative approaches and applications. Yet, the superior
performance and modeling flexibility of transformers came with a severe
increase in computation costs, and hence several works have proposed methods to
reduce this burden. Inspired by a cost-cutting method originally proposed for
language models, Data Multiplexing (DataMUX), we propose a novel approach for
efficient visual recognition that employs additional dim1 batching (i.e.,
concatenation) that greatly improves the throughput with little compromise in
the accuracy. We first introduce a naive adaptation of DataMux for vision
models, Image Multiplexer, and devise novel components to overcome its
weaknesses, rendering our final model, ConcatPlexer, at the sweet spot between
inference speed and accuracy. The ConcatPlexer was trained on ImageNet1K and
CIFAR100 dataset and it achieved 23.5% less GFLOPs than ViT-B/16 with 69.5% and
83.4% validation accuracy, respectively.

通过引入一种新的方法，即 DataMUX，本研究在视觉识别方面提出了一种名为 ConcatPlexer 的模型，成功地在推理速度和准确性之间找到了一个平衡点。该模型在 ImageNet1K 和 CIFAR100 数据集上训练，与 ViT-B/16 相比，GFLOPs 降低了 23.5%，验证准确率分别为 69.5% 和 83.4%。