DSP: Dynamic Semantic Prototype for Generative Zero-Shot Learning

ICLR 2023(2023)

Cited 0|Views25
No score
Generative models (e.g., generative adversarial network (GAN)) have advanced zero-shot learning (ZSL). Studies on the generative ZSL methods typically produce visual features of unseen classes to mitigate the issue of lacking unseen samples based on the predefined class semantic prototypes. As these empirically designed prototypes are not able to faithfully represent the actual semantic prototypes of visual features (i.e., visual prototypes), existing methods limit their ability to synthesize visual features that accurately represent real features and prototypes. We formulate this phenomenon as a visual-semantic domain shift problem. It prevents the generative models from further improving the ZSL performance. In this paper, we propose a dynamic semantic prototype learning (DSP) method to align the empirical and actual semantic prototypes for synthesizing accurate visual features. The alignment is conducted by jointly refining semantic prototypes and visual features so that the generator synthesizes visual features which are close to the real ones. We utilize a visual$\rightarrow$semantic mapping network (V2SM) to map both the synthesized and real features into the class semantic space. The V2SM benefits the generator to synthesize visual representations with rich semantics. The real/synthesized visual features supervise our visual-oriented semantic prototype evolving network (VOPE) where the predefined class semantic prototypes are iteratively evolved to become dynamic semantic prototypes. Such prototypes are then fed back to the generative network as conditional supervision. Finally, we enhance visual features by fusing the evolved semantic prototypes into their corresponding visual features. Our extensive experiments on three benchmark datasets show that our DSP improves existing generative ZSL methods, \textit{e.g.}, the average improvements of the harmonic mean over four baselines (e.g., CLSWGAN, f-VAEGAN, TF-VAEGAN and FREE) by 8.5\%, 8.0\% and 9.7\% on CUB, SUN and AWA2, respectively.
Translated text
Key words
Zero-Shot Learning,Generative Model,Knowledge Transfer
AI Read Science
Must-Reading Tree
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined