Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences
This work addresses the problem of improving invariance in image features for computer vision, offering a method applicable beyond convolutional models, though it appears incremental as it builds on existing pooling techniques.
The paper tackled the challenge of learning invariant image representations by proposing a novel pooling method that learns soft clustering from image sequences to improve temporal coherence with minimal information loss. Experiments on natural videos showed that auto-pooling outperformed traditional spatial pooling in image classification tasks, even without using spatial topology.
Learning invariant representations from images is one of the hardest challenges facing computer vision. Spatial pooling is widely used to create invariance to spatial shifting, but it is restricted to convolutional models. In this paper, we propose a novel pooling method that can learn soft clustering of features from image sequences. It is trained to improve the temporal coherence of features, while keeping the information loss at minimum. Our method does not use spatial information, so it can be used with non-convolutional models too. Experiments on images extracted from natural videos showed that our method can cluster similar features together. When trained by convolutional features, auto-pooling outperformed traditional spatial pooling on an image classification task, even though it does not use the spatial topology of features.