Interventional Few-Shot Learning
By Zhongqi Yue, Hanwang Zhang, Qianru Sun, Xiansheng Hua. 2020
277 citations recorded by the source corpus.
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal Model (SCM) for the causalities among the pre-trained knowledge, sample features, and labels. Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view. It is worth noting that the contribution of IFSL is orthogonal to existing fine-tuning and meta-learning based FSL methods, hence IFSL can improve all of them, achieving a new 1-/5-shot state-of-the-art on \textit{mini}ImageNet, \textit{tiered}ImageNet, and cross-domain CUB. Code is released at this https URL.
Subfields: Meta & Continual Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Meta & Continual Learning
Citations in the corpus
- GPT Understands, Too (2021, background): “Even for the many-shot finetuning setting, these models are still too large to memorize the fine-tuning samples (Yue et al., 2020) quickly.”
- Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima (2021, methodology): “Current few-shot methods mainly include optimization-based methods [12, 23, 32, 39, 45, 46, 55] and metric-based methods [13, 19, 44, 49, 52, 58, 57, 53].”
- Few-Shot Incremental Learning with Continually Evolved Classifiers (2021, methodology): “Optimization-based methods [8,16,24,28,29,36,37,50] and metric-based methods [9, 12, 35, 42, 46, 47, 51, 52] are two main lines of efforts.”
- Distilling Causal Effect of Data in Class-Incremental Learning (2021, methodology): “It has been recently introduced to various computer vision fields, including feature learning [3, 46], few-shot classification [49], long-tailed recognition [40], semantic segmentation [8] and other high-level vision tasks[41, 32, 48, 27].”
- Counterfactual VQA: A Cause-Effect Look at Language Bias (2020, background): “Counterfactual thinking and causal inference have inspired several studies in computer vision, including visual explanations [20, 7, 42, 48], scene graph generation [12, 38], image recognition [38], video analysis [16, 26], zero-shot and few-shot learning [50, 49] incremental learning [22], represen”
- Causal Intervention for Weakly-Supervised Semantic Segmentation (2020, background): “Recently, there is a growing number of computer vision tasks that benefit from causality [34, 40, 51, 52, 56, 63, 65].”
- Conterfactual Generative Zero-Shot Semantic Segmentation (2021, methodology): “image caption [19, 20]; direct and indirect effect help to generate unbiased scene graph [21]; counterfactual causality was widely used in visual question answer (VQA) problem and long-tailed classification [22, 23].”
- DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning (2020, methodology): “Besides the two popular approaches, many other promising methods have also been proposed to tackle the few-shot classification problem, such as works based on graph theories [66], [67], [68], [69], reinforcement learning [70], differentiable SVM [71], generative models [72], [73], [74], [75], [76], ”
- Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect (2020, unknown): “Recently, causal inference has also attracted increasing attention in computer vision society [39–44] for removing the dataset bias in domain-specific applications, e.g. , using pure direct effect to capture the spurious bias in VQA [41] and NWGM for Captioning [42].”