SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost

11/05/2021
by   Yanpeng Sun, et al.
16

The pixel-wise dense prediction tasks based on weakly supervisions currently use Class Attention Maps (CAM) to generate pseudo masks as ground-truth. However, the existing methods typically depend on the painstaking training modules, which may bring in grinding computational overhead and complex training procedures. In this work, the semantic structure aware inference (SSA) is proposed to explore the semantic structure information hidden in different stages of the CNN-based network to generate high-quality CAM in the model inference. Specifically, the semantic structure modeling module (SSM) is first proposed to generate the class-agnostic semantic correlation representation, where each item denotes the affinity degree between one category of objects and all the others. Then the structured feature representation is explored to polish an immature CAM via the dot product operation. Finally, the polished CAMs from different backbone stages are fused as the output. The proposed method has the advantage of no parameters and does not need to be trained. Therefore, it can be applied to a wide range of weakly-supervised pixel-wise dense prediction tasks. Experimental results on both weakly-supervised object localization and weakly-supervised semantic segmentation tasks demonstrate the effectiveness of the proposed method, which achieves the new state-of-the-art results on these two tasks.

READ FULL TEXT

page 2

page 3

page 4

page 7

page 8

research
03/07/2018

Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation receives much research attention...
research
03/30/2020

Same Features, Different Day: Weakly Supervised Feature Learning for Seasonal Invariance

"Like night and day" is a commonly used expression to imply that two thi...
research
07/09/2023

Reducing False Alarms in Video Surveillance by Deep Feature Statistical Modeling

Detecting relevant changes is a fundamental problem of video surveillanc...
research
05/11/2018

Weakly Supervised Domain-Specific Color Naming Based on Attention

The majority of existing color naming methods focuses on the eleven basi...
research
01/20/2022

Predicting Vegetation Stratum Occupancy from Airborne LiDAR Data with Deep Learning

We propose a new deep learning-based method for estimating the occupancy...
research
11/20/2018

Weakly Supervised Estimation of Shadow Confidence Maps in Ultrasound Imaging

Detecting acoustic shadows in ultrasound images is important in many cli...
research
03/27/2021

Few-shot Semantic Image Synthesis Using StyleGAN Prior

This paper tackles a challenging problem of generating photorealistic im...

Please sign up or login with your details

Forgot password? Click here to reset