computer-vision-9
Compositional Zero-Shot Learning
3260 papers • 126 benchmarks • 313 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 )
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in compositional-zero-shot-learning-9
Trend
Dataset
Best Model
Actions
MIT-States
MIT-States
MIT-States, generalized split
MIT-States, generalized split
UT-Zappos
Libraries
iUse these libraries to find compositional-zero-shot-learning-9 models and implementations
3 papers 118
Datasets
Subtasks
No subtasks available.
Most implemented papers
Open World Compositional Zero-Shot Learning
Yongqin Xian, Zeynep Akata, Muhammad Ferjad Naeem, Massimiliano Mancini•Thu Jan 28 2021
While the simple CZSL model achieves state-of-the-art performances in the closed world scenario, the feasibility scores boost the performance of the approach in the open world setting, clearly outperforming the previous state of the art.
163
