Attention-Guided Supervised Contrastive Learning for Semantic Segmentation

by   Ho Hin Lee, et al.

Contrastive learning has shown superior performance in embedding global and spatial invariant features in computer vision (e.g., image classification). However, its overall success of embedding local and spatial variant features is still limited, especially for semantic segmentation. In a per-pixel prediction task, more than one label can exist in a single image for segmentation (e.g., an image contains both cat, dog, and grass), thereby it is difficult to define 'positive' or 'negative' pairs in a canonical contrastive learning setting. In this paper, we propose an attention-guided supervised contrastive learning approach to highlight a single semantic object every time as the target. With our design, the same image can be embedded to different semantic clusters with semantic attention (i.e., coerce semantic masks) as an additional input channel. To achieve such attention, a novel two-stage training strategy is presented. We evaluate the proposed method on multi-organ medical image segmentation task, as our major task, with both in-house data and BTCV 2015 datasets. Comparing with the supervised and semi-supervised training state-of-the-art in the backbone of ResNet-50, our proposed pipeline yields substantial improvement of 5.53 segmentation cohorts respectively. The performance of the proposed method on natural images is assessed via PASCAL VOC 2012 dataset, and achieves 2.75 substantial improvement.


page 2

page 4

page 17


Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation

We present a novel semi-supervised semantic segmentation method which jo...

Contrastive learning of global and local features for medical image segmentation with limited annotations

A key requirement for the success of supervised deep learning is a large...

Positive-Negative Equal Contrastive Loss for Semantic Segmentation

The contextual information is critical for various computer vision tasks...

MMGL: Multi-Scale Multi-View Global-Local Contrastive learning for Semi-supervised Cardiac Image Segmentation

With large-scale well-labeled datasets, deep learning has shown signific...

Min-Max Similarity: A Contrastive Learning Based Semi-Supervised Learning Network for Surgical Tools Segmentation

Segmentation of images is a popular topic in medical AI. This is mainly ...

Deep Object Co-segmentation via Spatial-Semantic Network Modulation

Object co-segmentation is to segment the shared objects in multiple rele...

DA-RefineNet:A Dual Input Whole Slide Image Segmentation Algorithm Based on Attention

Due to the high resolution of pathological images, the automated semanti...

Please sign up or login with your details

Forgot password? Click here to reset