Few-Shot Image Recognition With Knowledge Transfer

By Zhimao Peng, Zechao Li, Junge Zhang, Yan Li, Guo-Jun Qi, Jinhui Tang. 2019

232 citations recorded by the source corpus.

Human can well recognize images of novel categories just after browsing few examples of these categories. One possible reason is that they have some external discriminative visual information about these categories from their prior knowledge. Inspired from this, we propose a novel Knowledge Transfer Network architecture (KTN) for few-shot image recognition. The proposed KTN model jointly incorporates visual feature learning, knowledge inferring and classifier learning into one unified framework for their optimal compatibility. First, the visual classifiers for novel categories are learned based on the convolutional neural network with the cosine similarity optimization. To fully explore the prior knowledge, a semantic-visual mapping network is then developed to conduct knowledge inference, which enables to infer the classifiers for novel categories from base categories. Finally, we design an adaptive fusion scheme to infer the desired classifiers by effectively integrating the above knowledge and visual information. Extensive experiments are conducted on two widely-used Mini-ImageNet and ImageNet Few-Shot benchmarks to evaluate the effectiveness of the proposed method. The results compared with the state-of-the-art approaches show the encouraging performance of the proposed method, especially on 1-shot and 2-shot tasks.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology, 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 Artificial Intelligence

1. Dacheng Tao
2. Zeynep Akata
3. Trevor Darrell
4. Jianping Gou
5. S. Maybank
6. Baosheng Yu
7. Bernt Schiele
8. Martin Schiegg

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Luc Van Gool
3. Trevor Darrell
4. Xiaogang Wang
5. Bernt Schiele
6. Zeynep Akata
7. Ming-Hsuan Yang
8. Yi Yang

In Media Technology

1. Dacheng Tao
2. S. Maybank
3. Max Welling
4. Zeynep Akata
5. Jianping Gou

In Meta & Continual Learning

1. Dacheng Tao
2. Max Welling
3. Zeynep Akata

Citations in the corpus

• Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? (2020, neutral): “64 KTN(Visual) [35] 64-64-64-64 54.”
• Knowledge Distillation: A Survey (2020, methodology): “Recently, knowledge distillation has been used successfully for solving the complex image classification problems (Zhu et al. 2019; Bagherinezhad et al. 2018; Peng et al. 2019b; Li and Hoiem 2017; Chen et al. 2018a; Wang et al. 2019b; Mukherjee et al. 2019).”
• Delving Deep Into Label Smoothing (2020, unknown): “Knowledge distillation has been widely used in many tasks [35], [36], [37], [38].”
• Relational Generalized Few-Shot Learning (2019, methodology): “, to regularize the feature space with textual embeddings for alignment on a distributional level [43], to use attention mechanisms for synthesizing additional training examples for few-shot classes [42], or to match a visual classifier with a knowledge-based representation [32].”