Rectifying the Shortcut Learning of Background for Few-Shot Learning
arXiv:2107.07746
Abstract
The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL). In this paper, we for the first time empirically identify image background, common in realistic images, as a shortcut knowledge helpful for in-class classification but ungeneralizable beyond training categories in FSL. A novel framework, COSOC, is designed to tackle this problem by extracting foreground objects in images at both training and evaluation without any extra supervision. Extensive experiments carried on inductive FSL tasks demonstrate the effectiveness of our approaches.
arXiv commentNeurIPS 2021
References in corpus (18)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Bootstrap your own latent: A new approach to self-supervised Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
- ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
- Delta-encoder: an effective sample synthesis method for few-shot object recognition
- Meta-Learning with Implicit Gradients
- Fast Context Adaptation via Meta-Learning
- Cross Attention Network for Few-shot Classification
- Interventional Few-Shot Learning
- Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
- TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
- Low-Shot Learning from Imaginary Data
- Image Deformation Meta-Networks for One-Shot Learning
- Learning Dynamic Alignment via Meta-filter for Few-shot Learning
- Boosting Few-Shot Learning With Adaptive Margin Loss
- Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning