Rectifying the Shortcut Learning of Background for Few-Shot Learning
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.
Code (1)
Tasks
Few-Shot Image ClassificationFew-Shot LearningImage ClassificationSimilar Papers 제목 키워드 기반
Rectify ViT Shortcut Learning by Visual Saliency
Shortcut learning is common but harmful to deep learning models, leading to degenerated feature representations and consequently jeopardizing the model's generalizability and interpretability. However, shortcut learning …
Overcoming Shortcut Problem in VLM for Robust Out-of-Distribution Detection
Vision-language models (VLMs), such as CLIP, have shown remarkable capabilities in downstream tasks. However, the coupling of semantic information between the foreground and the background in images leads to signific…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionSR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
The existing Zero-Shot learning (ZSL) methods may suffer from the vague class attributes that are highly overlapped for different classes. Unlike these methods that ignore the discrimination among classes, in this paper,…
Generative Adversarial NetworkZero-Shot LearningDomain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation
Few-shot semantic segmentation (FSS) has achieved great success on segmenting objects of novel classes, supported by only a few annotated samples. However, existing FSS methods often underperform in the presence of domai…
Cross-Domain Few-ShotFew-Shot Semantic SegmentationSegmentationSemantic SegmentationRectifying Shortcut Behaviors in Preference-based Reward Learning
In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to r…
Reinforcement Learning