Neuroevolution of Self-Attention Over Proto-Objects
This reduces computational overhead for visual reinforcement learning tasks, though it is an incremental improvement over existing patch-based methods.
The paper tackles the problem of high computational cost in visual attention mechanisms by replacing traditional rectangular image patches with proto-objects (image regions sharing visual properties), achieving state-of-the-art performance with 62% fewer parameters and 2.6 times less training time.
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.