Consistent Structural Relation Learning for Zero-Shot Segmentation

By Peike Li, Yunchao Wei, Yi Yang. 2020

88 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Language-driven Semantic Segmentation (2022, background): “Hu et al. (2020) propose to use uncertainty-aware learning to better handle noisy labels of seen classes, while Li et al. (2020b) introduce a structured learning approach to better exploit the relations between seen and unseen categories.”
GroupViT: Semantic Segmentation Emerges from Text Supervision (2022, background): “Going further, zero-shot approaches [6, 38] are proposed to learn segmentation models for unseen categories without using pixel-wise labels for them.”
Domain Consensus Clustering for Universal Domain Adaptation (2021, background): “As a feasible solution, unsupervised domain adaptation (UDA) [45] tries to solve this by transferring the knowledge from an annotated domain to an unlabeled domain, and has achieved significant progress in multiple tasks [33, 34, 27, 29, 35, 37].”
Open-Vocabulary Image Segmentation (2021, methodology): “These baselines have already surpassed the performances in existing zero-shot image segmentation meth-ods [4, 6, 19, 28, 47] on several datasets due to large-scale image-text pre-training.”
Scaling Open-Vocabulary Image Segmentation with Image-Level Labels (2021, methodology): “Zero-shot semantic segmentation methods [6,49,20,30,4] aim to segment images with unseen visual concepts using language embeddings.”
Extract Free Dense Labels from CLIP (2021, background): “Other studies like [26], [34], and [20], improve the generative ZS3Net in terms of uncertainty, structural consistency, and context, respectively, while STRICT [41] boosts the SPNet through self-training.”
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-Language Model (2021, methodology): “Different from [5,32,20], SPNet [48] attempt to mapping vision feature to the semantic space via word embedding.”
Image Segmentation Using Text and Image Prompts (2021, background): “Follow-up work explicitly models the relation between seen and unseen classes [26].”
DenseCLIP: Extract Free Dense Labels from CLIP (2021, background): “Other studies like [26], [34], and [20], improve the generative ZS3Net in terms of uncertainty, structural consistency, and context, respectively, while STRICT [41] boosts the SPNet through self-training.”
Conterfactual Generative Zero-Shot Semantic Segmentation (2021, background): “Most of the new works follow these two works and import new knowledge resources like context [14, 24] and relationships between classes [26] to help generate more ﬁtting fake features.”