Displaying 75 resources
Software resources Software resources

Word-Class Embeddings for Multiclass Text Classification

Code for Word-Class Embeddings (WCEs), a form of supervised embeddings especially suited for multiclass text classification.

Category
Semantic knowledge, Technology methodologies and landscape
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

CO2A – Contrastive Conditional domain Alignment

A novel unsupervised domain adaptation approach for action recognition from videos, inspired by recent literature on contrastive learning.

Category
Multi-modal interaction, Sensing of motion and mechanical properties
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

Neighborhood Contrastive Learning for Novel Class Discovery

A holistic learning framework for Novel Class Discovery (NCD), which adopts contrastive learning to learn discriminate features with both the labeled and unlabeled data.

Category
Semantic knowledge
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

PandA: Unsupervised learning of parts and appearances in the feature maps of GANs

We propose an architecture-agnostic approach that jointly discovers factors representing spatial parts and their appearances in an entirely unsupervised fashion.

Category
System architectures
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning

Exemplar-free class-incremental learning is very challenging due to the negative effect of catastrophic forgetting.

Category
Technology methodologies and landscape
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e
Software resources Software resources

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only synthetic data.

Category
Semantic knowledge
Target audience
ADR Experts and Associations, Researchers and Academic
Source
Adra-e