Weak-shot Fine-grained Classification via Similarity Transfer
arXiv:2009.09197
Abstract
Recognizing fine-grained categories remains a challenging task, due to the subtle distinctions among different subordinate categories, which results in the need of abundant annotated samples. To alleviate the data-hungry problem, we consider the problem of learning novel categories from web data with the support of a clean set of base categories, which is referred to as weak-shot learning. In this setting, we propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories. Specifically, we firstly train a similarity net on clean data, and then leverage the transferred similarity to denoise web training data using two simple yet effective strategies. In addition, we apply adversarial loss on similarity net to enhance the transferability of similarity. Comprehensive experiments demonstrate the effectiveness of our weak-shot setting and our SimTrans method. Datasets and codes are available at https://github.com/bcmi/SimTrans-Weak-Shot-Classification.
arXiv commentaccepted by NeurIPS2021
References in corpus (19)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels
- Fine-Grained Visual Classification of Aircraft
- A Simple Neural Attentive Meta-Learner
- Zero-Shot Learning by Convex Combination of Semantic Embeddings
- Training Convolutional Networks with Noisy Labels
- DivideMix: Learning with Noisy Labels as Semi-supervised Learning
- WebVision Database: Visual Learning and Understanding from Web Data
- Meta-Learning with Latent Embedding Optimization
- Learning to cluster in order to transfer across domains and tasks
- Joint Optimization Framework for Learning with Noisy Labels
- Zero-Shot Learning -- The Good, the Bad and the Ugly
- Combating noisy labels by agreement: A joint training method with co-regularization
- Learning From Noisy Large-Scale Datasets With Minimal Supervision
- Semi-supervised Zero-Shot Learning by a Clustering-based Approach
- CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
- Deep Self-Learning From Noisy Labels
- Learning from Noisy Web Data with Category-level Supervision