Weak Novel Categories without Tears: A Survey on Weak-Shot Learning

Abstract

Deep learning is a data-hungry approach, which requires massive training data. However, it is time-consuming and labor-intensive to collect abundant fully-annotated training data for all categories. Assuming the existence of base categories with adequate fully-annotated training samples, different paradigms requiring fewer training samples or weaker annotations for novel categories have attracted growing research interest. Among them, zero-shot (resp., few-shot) learning explores using zero (resp., a few) training samples for novel categories, which lowers the quantity requirement for novel categories. Instead, weak-shot learning lowers the quality requirement for novel categories. Specifically, sufficient training samples are collected for novel categories but they only have weak annotations. In different tasks, weak annotations are presented in different forms (e.g., noisy labels for image classification, image labels for object detection, bounding boxes for segmentation), similar to the definitions in weakly supervised learning. Therefore, weak-shot learning can also be treated as weakly supervised learning with auxiliary fully supervised categories. In this paper, we discuss the existing weak-shot learning methodologies in different tasks and summarize the codes at https://github.com/bcmi/Awesome-Weak-Shot-Learning.

References in corpus (12)

• Prototypical Networks for Few-shot Learning
• A Simple Neural Attentive Meta-Learner
• Zero-Shot Detection
• Learning From Noisy Large-Scale Datasets With Minimal Supervision
• Weakly Supervised Instance Segmentation using Class Peak Response
• ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
• Zero-Shot Object Detection by Hybrid Region Embedding
• FGN: Fully Guided Network for Few-Shot Instance Segmentation
• Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary
• Learning from Noisy Web Data with Category-level Supervision
• Cross-Supervised Object Detection
• Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity