About

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

Attributes as Operators: Factorizing Unseen Attribute-Object Compositions

ECCV 2018 Tushar-N/attributes-as-operators

In addition, we show that not only can our model recognize unseen compositions robustly in an open-world setting, it can also generalize to compositions where objects themselves were unseen during training.

COMPOSITIONAL ZERO-SHOT LEARNING IMAGE RETRIEVAL WITH MULTI-MODAL QUERY

Symmetry and Group in Attribute-Object Compositions

CVPR 2020 DirtyHarryLYL/SymNet

To model the compositional nature of these general concepts, it is a good choice to learn them through transformations, such as coupling and decoupling.

COMPOSITIONAL ZERO-SHOT LEARNING

A causal view of compositional zero-shot recognition

NeurIPS 2020 nv-research-israel/causal_comp

This leads to consistent misclassification of samples from a new distribution, like new combinations of known components.

COMPOSITIONAL ZERO-SHOT LEARNING

Learning Graph Embeddings for Compositional Zero-shot Learning

3 Feb 2021ExplainableML/czsl

In compositional zero-shot learning, the goal is to recognize unseen compositions (e. g. old dog) of observed visual primitives states (e. g. old, cute) and objects (e. g. car, dog) in the training set.

COMPOSITIONAL ZERO-SHOT LEARNING GRAPH EMBEDDING TRANSFER LEARNING

Open World Compositional Zero-Shot Learning

29 Jan 2021ExplainableML/czsl

After estimating the feasibility score of each composition, we use these scores to either directly mask the output space or as a margin for the cosine similarity between visual features and compositional embeddings during training.

COMPOSITIONAL ZERO-SHOT LEARNING