Task-Aware Feature Generation for Zero-Shot Compositional Learning

Understand

Visual concepts (e.g., red apple, big elephant) are often semantically compositional and each element of the compositions can be reused to construct novel concepts (e.g., red elephant).

• Compositional feature synthesis, which generates image feature distributions exploiting the semantic compositionality, is a promising approach to sample-efficient model generalization.
• In this work, we propose a task-aware feature generation (TFG) framework for compositional learning, which generates features of novel visual concepts by transferring knowledge from previously seen concepts.
• These synthetic features are then used to train a classifier to recognize novel concepts in a zero-shot manner.