Enregistré dans:
Détails bibliographiques
Auteurs principaux: Pinto, Rafael C., Tavares, Anderson R.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.00186
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
Table des matières:
  • Proto-objects - image regions that share common visual properties - offer a promising alternative to traditional attention mechanisms based on rectangular-shaped image patches in neural networks. Although previous work demonstrated that evolving a patch-based hard-attention module alongside a controller network could achieve state-of-the-art performance in visual reinforcement learning tasks, our approach leverages image segmentation to work with higher-level features. By operating on proto-objects rather than fixed patches, we significantly reduce the representational complexity: each image decomposes into fewer proto-objects than regular patches, and each proto-object can be efficiently encoded as a compact feature vector. This enables a substantially smaller self-attention module that processes richer semantic information. Our experiments demonstrate that this proto-object-based approach matches or exceeds the state-of-the-art performance of patch-based implementations with 62% less parameters and 2.6 times less training time.