Context-aware Feature Generation For Zero-shot Semantic Segmentation (2020-08-16T00:00:00.000000Z)

TL;DR

This paper proposes a novel context-aware feature generation method for zero-shot segmentation named CaGNet, which inserts a contextual module in a segmentation network to capture the pixel-wise contextual information, which guides the process of generating more diverse and context- aware features from semantic word embeddings.

Abstract

Existing semantic segmentation models heavily rely on dense pixel-wise annotations. To reduce the annotation pressure, we focus on a challenging task named zero-shot semantic segmentation, which aims to segment unseen objects with zero annotations. This task can be accomplished by transferring knowledge across categories via semantic word embeddings. In this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet. In particular, with the observation that a pixel-wise feature highly depends on its contextual information, we insert a contextual module in a segmentation network to capture the pixel-wise contextual information, which guides the process of generating more diverse and context-aware features from semantic word embeddings. Our method achieves state-of-the-art results on three benchmark datasets for zero-shot segmentation.

Authors

Li Niu

11 papers

Liqing Zhang

11 papers

Siyuan Zhou

4 papers

TL;DR

Abstract

Authors

References54 items

Zero-Shot Semantic Segmentation via Variational Mapping

Zero-shot Learning with Many Classes by High-rank Deep Embedding Networks

Zero-Shot Semantic Segmentation

Gradient Matching Generative Networks for Zero-Shot Learning

Semantic Projection Network for Zero- and Few-Label Semantic Segmentation

Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation

Out-Of-Distribution Detection for Generalized Zero-Shot Action Recognition

Leveraging the Invariant Side of Generative Zero-Shot Learning

F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning

Zero-Shot Learning via Category-Specific Visual-Semantic Mapping and Label Refinement

Pseudo Transfer with Marginalized Corrupted Attribute for Zero-shot Learning

GraphNet: Learning Image Pseudo Annotations for Weakly-Supervised Semantic Segmentation

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks

Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-Identification

Multi-modal Cycle-consistent Generalized Zero-Shot Learning

Webly Supervised Learning Meets Zero-shot Learning: A Hybrid Approach for Fine-Grained Classification

Harmonious Attention Network for Person Re-identification

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Feature Generating Networks for Zero-Shot Learning

Toward Multimodal Image-to-Image Translation

Squeeze-and-Excitation Networks

TextureGAN: Controlling Deep Image Synthesis with Texture Patches

Open Vocabulary Scene Parsing

Exploiting Saliency for Object Segmentation from Image Level Labels

COCO-Stuff: Thing and Stuff Classes in Context

Pyramid Scene Parsing Network

RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation

Least Squares Generative Adversarial Networks

Semi-Supervised Classification with Graph Convolutional Networks

Bag of Tricks for Efficient Text Classification

Zero-Shot Hashing via Transferring Supervised Knowledge

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Simple Does It: Weakly Supervised Instance and Semantic Segmentation

Deep Residual Learning for Image Recognition

Multi-Scale Context Aggregation by Dilated Convolutions

Semantic Segmentation based on Stacked Discriminative Autoencoders and Context-Constrained Weakly Supervised Learning

An embarrassingly simple approach to zero-shot learning

U-Net: Convolutional Networks for Biomedical Image Segmentation

Label-Embedding for Image Classification

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Transductive Multi-View Zero-Shot Learning

Fully convolutional networks for semantic segmentation

Evaluation of output embeddings for fine-grained image classification

ImageNet Large Scale Visual Recognition Challenge

The Pascal Visual Object Classes Challenge: A Retrospective

The Role of Context for Object Detection and Semantic Segmentation in the Wild

Composite Concept Discovery for Zero-Shot Video Event Detection

DeViSE: A Deep Visual-Semantic Embedding Model

Distributed Representations of Words and Phrases and their Compositionality

Semantic contours from inverse detectors

Learning to detect unseen object classes by between-class attribute transfer

Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks

Attribute-Based Classification for Zero-Shot Visual Object Categorization

Field of Study

Journal Information

Name

Venue Information

Name

Type

URL

Alternate Names