Compositional Zero-Shot Learning
24 papers with code • 4 benchmarks • 6 datasets
Compositional Zero-Shot Learning (CZSL) is a computer vision task in which the goal is to recognize unseen compositions fromed from seen state and object during training. The key challenge in CZSL is the inherent entanglement between the state and object within the context of an image. Some example benchmarks for this task are MIT-states, UT-Zappos, and C-GQA. Models are usually evaluated with the Accuracy for both seen and unseen compositions, as well as their Harmonic Mean(HM).
( Image credit: Heosuab )
Benchmarks
These leaderboards are used to track progress in Compositional Zero-Shot Learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Compositional Zero-Shot Learning models and implementations
MIT-States
UT Zappos50K
C-GQA
AO-CLEVr
UT-Zappos50K
Most implemented papers
Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
batsresearch/csp
•
•
We perform additional experiments to show that CSP improves generalization to higher-order attribute-attribute-object compositions (e. g., old white cat) and combinations of pretrained attributes and fine-tuned objects.
KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning
explainableml/kg-sp
•
•
CVPR 2022
The goal of open-world compositional zero-shot learning (OW-CZSL) is to recognize compositions of state and objects in images, given only a subset of them during training and no prior on the unseen compositions.
Disentangling Visual Embeddings for Attributes and Objects
We use visual decomposed features to hallucinate embeddings that are representative for the seen and novel compositions to better regularize the learning of our model.
Learning Invariant Visual Representations for Compositional Zero-Shot Learning
pris-cv/ivr
•
•
Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions using knowledge learned from seen attribute-object compositions in the training set.
Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning
xduxyli/scen-master
•
•
CVPR 2022
Some methods recognize state and object with two trained classifiers, ignoring the impact of the interaction between object and state; the other methods try to learn the joint representation of the state-object compositions, leading to the domain gap between seen and unseen composition sets.
Reference-Limited Compositional Zero-Shot Learning
Compositional zero-shot learning (CZSL) refers to recognizing unseen compositions of known visual primitives, which is an essential ability for artificial intelligence systems to learn and understand the world.
Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning
Existing methods either learn the combined state-object representation, challenging the generalization of unseen compositions, or design two classifiers to identify state and object separately from image features, ignoring the intrinsic relationship between them.
Learning Attention as Disentangler for Compositional Zero-shot Learning
The key to CZSL is learning the disentanglement of the attribute-object composition.
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
Recent compositional zero-shot learning (CZSL) methods adapt pre-trained vision-language models (VLMs) by constructing trainable prompts only for composed state-object pairs.
CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
zhaohengz/caila
•
•
In this paper, we study the problem of Compositional Zero-Shot Learning (CZSL), which is to recognize novel attribute-object combinations with pre-existing concepts.
