Active Visual Exploration Based on Attention-Map Entropy
This addresses active visual exploration for robotics or vision systems, but it is incremental as it builds on existing transformer-based methods with a simplified training approach.
The paper tackled the problem of active visual exploration with limited sensor capabilities by introducing Attention-Map Entropy (AME), which uses transformer model uncertainty to select informative observations without extra loss components, improving reconstruction, segmentation, and classification performance on public datasets.
Active visual exploration addresses the issue of limited sensor capabilities in real-world scenarios, where successive observations are actively chosen based on the environment. To tackle this problem, we introduce a new technique called Attention-Map Entropy (AME). It leverages the internal uncertainty of the transformer-based model to determine the most informative observations. In contrast to existing solutions, it does not require additional loss components, which simplifies the training. Through experiments, which also mimic retina-like sensors, we show that such simplified training significantly improves the performance of reconstruction, segmentation and classification on publicly available datasets.