Convolutional Networks as Extremely Small Foundation Models: Visual Prompting and Theoretical Perspective

TL;DR

This paper introduces a simple, theoretically grounded prompting module called SDForest that adapts generic deep networks for new tasks like video object segmentation, achieving competitive results with low computational cost.

Contribution

The paper proposes a novel, theoretically motivated prompting module, SDForest, combining nonparametric methods with deep networks for effective few-shot adaptation.

Findings

SDForest achieves real-time performance on CPU.

It attains competitive results on DAVIS2016 and DAVIS2017 datasets.

The approach has lower complexity and better generalization properties.

Abstract

Comparing to deep neural networks trained for specific tasks, those foundational deep networks trained on generic datasets such as ImageNet classification, benefits from larger-scale datasets, simpler network structure and easier training techniques. In this paper, we design a prompting module which performs few-shot adaptation of generic deep networks to new tasks. Driven by learning theory, we derive prompting modules that are as simple as possible, as they generalize better under the same training error. We use a case study on video object segmentation to experiment. We give a concrete prompting module, the Semi-parametric Deep Forest (SDForest) that combines several nonparametric methods such as correlation filter, random forest, image-guided filter, with a deep network trained for ImageNet classification task. From a learning-theoretical point of view, all these models are of significantly smaller VC dimension or complexity so tend to generalize better, as long as the empirical studies show that the training error of this simple ensemble can achieve comparable results from a end-to-end trained deep network. We also propose a novel methods of analyzing the generalization under the setting of video object segmentation to make the bound tighter. In practice, SDForest has extremely low computation cost and achieves real-time even on CPU. We test on video object segmentation tasks and achieve competitive performance at DAVIS2016 and DAVIS2017 with purely deep learning approaches, without any training or fine-tuning.