On Implicit Attribute Localization for Generalized Zero-Shot Learning
This work addresses generalized zero-shot learning for computer vision, providing a simpler and effective baseline, though it is incremental as it builds on existing backbones.
The paper tackled the problem of generalized zero-shot learning by showing that common backbones can implicitly localize attributes without explicit attention mechanisms, and proposed SELAR, a simple method that encourages this localization to achieve competitive performance, with results comparable to more complex state-of-the-art methods.
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions. Since attributes are often related to specific parts of objects, many recent works focus on discovering discriminative regions. However, these methods usually require additional complex part detection modules or attention mechanisms. In this paper, 1) we show that common ZSL backbones (without explicit attention nor part detection) can implicitly localize attributes, yet this property is not exploited. 2) Exploiting it, we then propose SELAR, a simple method that further encourages attribute localization, surprisingly achieving very competitive generalized ZSL (GZSL) performance when compared with more complex state-of-the-art methods. Our findings provide useful insight for designing future GZSL methods, and SELAR provides an easy to implement yet strong baseline.