Localizing by Describing: Attribute-Guided Attention Localization for Fine-Grained Recognition
This work addresses the problem of fine-grained recognition for computer vision researchers by providing a more efficient method that reduces annotation effort compared to traditional part-based approaches, though it is incremental in nature.
The paper tackles the challenge of localizing multiple discriminative regions in fine-grained recognition by introducing an attribute-guided attention localization scheme, which improves both fine-grained recognition and attribute recognition on the CUB-200-2011 dataset.
A key challenge in fine-grained recognition is how to find and represent discriminative local regions. Recent attention models are capable of learning discriminative region localizers only from category labels with reinforcement learning. However, not utilizing any explicit part information, they are not able to accurately find multiple distinctive regions. In this work, we introduce an attribute-guided attention localization scheme where the local region localizers are learned under the guidance of part attribute descriptions. By designing a novel reward strategy, we are able to learn to locate regions that are spatially and semantically distinctive with reinforcement learning algorithm. The attribute labeling requirement of the scheme is more amenable than the accurate part location annotation required by traditional part-based fine-grained recognition methods. Experimental results on the CUB-200-2011 dataset demonstrate the superiority of the proposed scheme on both fine-grained recognition and attribute recognition.