Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant computation on some area like the background. In this work, we encapsulate the idea of reducing spatial redundancy into a novel poll and pool (PnP) sampling module, with which we build an end-to-end PnP-DETR architecture that adaptively allocates its computation spatially to be more efficient. Concretely, the PnP module abstracts the image feature map into fine foreground object feature vectors and a small number of coarse background contextual feature vectors. The transformer models information interaction within the fine-coarse feature space and translates the features into the detection result. Moreover, the PnP-augmented model can instantly achieve various desired trade-offs between performance and computation with a single model by varying the sampled feature length, without requiring to train multiple models as existing methods. Thus it offers greater flexibility for deployment in diverse scenarios with varying computation constraint. We further validate the generalizability of the PnP module on panoptic segmentation and the recent transformer-based image recognition model ViT and show consistent efficiency gain. We believe our method makes a step for efficient visual analysis with transformers, wherein spatial redundancy is commonly observed. Code will be available at \url{https://github.com/twangnh/pnp-detr}.
翻译:最近,DETR率先以变压器为愿景任务解决方案, 它直接将图像特征地图转换为天体探测结果。 尽管效果有效, 翻译完整特征地图可能由于背景等某些领域的冗余计算而成本高昂。 在这项工作中, 我们将减少空间冗余的想法包罗成一个新的民意测验和池( PnP) 抽样模块, 通过这个模块,我们可以立即用单一模型实现各种预期的性能和计算之间的权衡, 以不同的抽样特征长度, 不需要用现有方法来培训多种模型。 具体地说, PnP模块将图像特征地图转换成精细的地表对象特性矢量和少量的粗化背景背景特性矢量。 在精细的视野特征空间空间空间空间空间里, 变动模型信息互动, 并将这些特性转换成检测结果。 此外, PnP 推荐模型可以立即通过一个单一模型实现各种预期的性能和计算结果, 不需要将多种模型作为现有方法加以培训。 因此, 更灵活地在不同的计算限制下部署各种情景。 我们进一步验证 PnPP 的通用模型的可建模性背景背景背景特性, 在常规的图像分析中, 我们的变压分析中, 将有一个常规的变式的变压式的图像分析, 和常规的变式的变式的变式的变式的变式的变式的变式的变式的图像, 。