.png){kind=icon}
返回
AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling
.png){kind=icon}
OA
AI
DOI：10.1109/TIP.2022.3227503.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of proceeding convolutional operations. Their goal is to produce downsampled volumes that closely resemble the input volume while, ideally, also being computationally and memory efficient. Meeting both these requirements remains a challenge. To this end, we propose an adaptive and exponentially weighted pooling method: adaPool. Our method learns a regional-specific fusion of two sets of pooling kernels that are based on the exponent of the Dice-Sorensen coefficient and the exponential maximum, respectively. AdaPool improves the preservation of detail on a range of tasks including image and video classification and object detection. A key property of adaPool is its bidirectional nature. In contrast to common pooling methods, the learned weights can also be used to upsample activation maps. We term this method adaUnPool. We evaluate adaUnPool on image and video super-resolution and frame interpolation. For benchmarking, we introduce Inter4K, a novel high-quality, high frame-rate video dataset. Our expaeriments demonstrate that adaPool systematically achieves better results across tasks and backbones, while introducing a minor additional computational and memory overhead.
Keyword:
Kernel
Task analysis
Interpolation
Superresolution
Computer architecture
Weight measurement
Visualization
Pooling
downsampling
upsampling
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
.png){kind=icon}
Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
PREAI
分享收藏The influence of various precursors on solar-light-driven g-C3N4 synthesis and its effect on photocatalytic tetracycline hydrochloride (TCH) degradation各种前体对太阳光驱动的g-C3N4合成及其对光催化盐酸四环素 (TCH) 降解的影响
PREAI
分享收藏
查看更多内容