AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling

11/01/2021
by   Alexandros Stergiou, et al.
7

Pooling layers are essential building blocks of Convolutional Neural Networks (CNNs) that reduce computational overhead and increase the receptive fields of proceeding convolutional operations. They aim to produce downsampled volumes that closely resemble the input volume while, ideally, also being computationally and memory efficient. It is a challenge to meet both requirements jointly. To this end, we propose an adaptive and exponentially weighted pooling method named adaPool. Our proposed method uses a parameterized fusion of two sets of pooling kernels that are based on the exponent of the Dice-Sorensen coefficient and the exponential maximum, respectively. A key property of adaPool is its bidirectional nature. In contrast to common pooling methods, weights can be used to upsample a downsampled activation map. We term this method adaUnPool. We demonstrate how adaPool improves the preservation of detail through a range of tasks including image and video classification and object detection. We then evaluate adaUnPool on image and video frame super-resolution and frame interpolation tasks. For benchmarking, we introduce Inter4K, a novel high-quality, high frame-rate video dataset. Our combined experiments demonstrate that adaPool systematically achieves better results across tasks and backbone architectures, while introducing a minor additional computational and memory overhead.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 13

research
04/02/2021

LiftPool: Bidirectional ConvNet Pooling

Pooling is a critical operation in convolutional neural networks for inc...
research
02/27/2020

RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference

Pooling operators are key components in most Convolutional Neural Networ...
research
01/24/2023

Progressive Meta-Pooling Learning for Lightweight Image Classification Model

Practical networks for edge devices adopt shallow depth and small convol...
research
09/16/2022

Self-Attentive Pooling for Efficient Deep Learning

Efficient custom pooling techniques that can aggressively trim the dimen...
research
04/11/2018

Detail-Preserving Pooling in Deep Networks

Most convolutional neural networks use some method for gradually downsca...
research
11/14/2014

A Discriminative CNN Video Representation for Event Detection

In this paper, we propose a discriminative video representation for even...
research
04/08/2020

Deep Adaptive Inference Networks for Single Image Super-Resolution

Recent years have witnessed tremendous progress in single image super-re...

Please sign up or login with your details

Forgot password? Click here to reset