Probabilistic Attention for Interactive Segmentation
This work addresses interactive segmentation for annotators to improve annotation efficiency, presenting a novel method for a known bottleneck.
The authors tackled the problem of interactive semantic segmentation by providing a probabilistic interpretation of attention, showing that standard dot-product attention is a special case of MAP inference. They observed that key adaptation boosts model performance by ~10% mIoU in low feedback regimes and value propagation improves responsiveness in high feedback regimes.
We provide a probabilistic interpretation of attention and show that the standard dot-product attention in transformers is a special case of Maximum A Posteriori (MAP) inference. The proposed approach suggests the use of Expectation Maximization algorithms for online adaptation of key and value model parameters. This approach is useful for cases in which external agents, e.g., annotators, provide inference-time information about the correct values of some tokens, e.g, the semantic category of some pixels, and we need for this new information to propagate to other tokens in a principled manner. We illustrate the approach on an interactive semantic segmentation task in which annotators and models collaborate online to improve annotation efficiency. Using standard benchmarks, we observe that key adaptation boosts model performance ($\sim10\%$ mIoU) in the low feedback regime and value propagation improves model responsiveness in the high feedback regime. A PyTorch layer implementation of our probabilistic attention model will be made publicly available here: https://github.com/apple/ml-probabilistic-attention.