Top-Down Networks: A coarse-to-fine reimagination of CNNs

04/16/2020
by   Ioannis Lelekas, et al.
69

Biological vision adopts a coarse-to-fine information processing pathway, from initial visual detection and binding of salient features of a visual scene, to the enhanced and preferential processing given relevant stimuli. On the contrary, CNNs employ a fine-to-coarse processing, moving from local, edge-detecting filters to more global ones extracting abstract representations of the input. In this paper we reverse the feature extraction part of standard bottom-up architectures and turn them upside-down: We propose top-down networks. Our proposed coarse-to-fine pathway, by blurring higher frequency information and restoring it only at later stages, offers a line of defence against adversarial attacks that introduce high frequency noise. Moreover, since we increase image resolution with depth, the high resolution of the feature map in the final convolutional layer contributes to the explainability of the network's decision making process. This favors object-driven decisions over context driven ones, and thus provides better localized class activation maps. This paper offers empirical evidence for the applicability of the top-down resolution processing to various existing architectures on multiple visual tasks.

READ FULL TEXT

page 1

page 5

page 7

page 13

page 14

page 15

research
03/02/2023

A Coarse to Fine Framework for Object Detection in High Resolution Image

Object detection is a fundamental problem in computer vision, aiming at ...
research
08/06/2018

Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform

Dense pixelwise prediction such as semantic segmentation is an up-to-dat...
research
03/16/2023

Fine-Grained and High-Faithfulness Explanations for Convolutional Neural Networks

Recently, explaining CNNs has become a research hotspot. CAM (Class Acti...
research
06/02/2020

Channel Attention based Iterative Residual Learning for Depth Map Super-Resolution

Despite the remarkable progresses made in deep-learning based depth map ...
research
03/01/2021

Coarse-Fine Networks for Temporal Activity Detection in Videos

In this paper, we introduce 'Coarse-Fine Networks', a two-stream archite...
research
04/08/2021

Progressive Semantic Segmentation

The objective of this work is to segment high-resolution images without ...
research
04/26/2022

Coarse-to-fine Q-attention with Tree Expansion

Coarse-to-fine Q-attention enables sample-efficient robot manipulation b...

Please sign up or login with your details

Forgot password? Click here to reset