Visual semantic segmentation based on few/zero-shot learning: An overview
Visual semantic segmentation aims at separating a visual sample into diverse blocks with
specific semantic attributes and identifying the category for each block, and it plays a crucial …
specific semantic attributes and identifying the category for each block, and it plays a crucial …
Self-support few-shot semantic segmentation
Existing few-shot segmentation methods have achieved great progress based on the
support-query matching framework. But they still heavily suffer from the limited coverage of …
support-query matching framework. But they still heavily suffer from the limited coverage of …
Holistic prototype activation for few-shot segmentation
Conventional deep CNN-based segmentation approaches have achieved satisfactory
performance in recent years, however, they are essentially Big Data-driven technologies …
performance in recent years, however, they are essentially Big Data-driven technologies …
An overview on Meta-learning approaches for Few-shot Weakly-supervised Segmentation
Semantic segmentation is a difficult task in computer vision that have applications in many
scenarios, often as a preprocessing step for a tool. Current solutions are based on Deep …
scenarios, often as a preprocessing step for a tool. Current solutions are based on Deep …
Cpcm: Contextual point cloud modeling for weakly-supervised point cloud semantic segmentation
We study the task of weakly-supervised point cloud semantic segmentation with sparse
annotations (eg, less than 0.1% points are labeled), aiming to reduce the expensive cost of …
annotations (eg, less than 0.1% points are labeled), aiming to reduce the expensive cost of …
Learning expressive prompting with residuals for vision transformers
Prompt learning is an efficient approach to adapt transformers by inserting learnable set of
parameters into the input and intermediate representations of a pre-trained model. In this …
parameters into the input and intermediate representations of a pre-trained model. In this …
Msanet: Multi-similarity and attention guidance for boosting few-shot segmentation
Few-shot segmentation aims to segment unseen-class objects given only a handful of
densely labeled samples. Prototype learning, where the support feature yields a singleor …
densely labeled samples. Prototype learning, where the support feature yields a singleor …
Video semantic segmentation via sparse temporal transformer
Currently, video semantic segmentation mainly faces two challenges: 1) the demand of
temporal consistency; 2) the balance between segmentation accuracy and inference …
temporal consistency; 2) the balance between segmentation accuracy and inference …
Das: Densely-anchored sampling for deep metric learning
Abstract Deep Metric Learning (DML) serves to learn an embedding function to project
semantically similar data into nearby embedding space and plays a vital role in many …
semantically similar data into nearby embedding space and plays a vital role in many …
Prediction calibration for generalized few-shot semantic segmentation
Generalized Few-shot Semantic Segmentation (GFSS) aims to segment each image pixel
into either base classes with abundant training examples or novel classes with only a …
into either base classes with abundant training examples or novel classes with only a …