SemGIF: A Semantics Guided Incremental Few-shot Learning Framework with Generative Replay
By S. Divakar Bhat, Biplab Banerjee, Subhasis Chaudhuri. 2021
3 citations recorded by the source corpus.
We address the problem of incremental few-shot learning (IFSL) by leveraging the notion of generative feature replay. Learning novel concepts while preserving old knowledge is a long-lasting challenge in machine learning. The main concern in IFSL is to combat the catastrophic forgetting of the base classes whose training data are not available during the incremental stage while ensuring good generalization for the few-shot classes. Existing techniques prefer to preserve some base class samples to tackle forgetting, which does not comply with the intention of incremental learning. To this end, we propose a novel framework called Semantics Guided IFSL (SemGIF), which trains a generative model to synthesize base class samples on demand during the incremental step. Considering the importance of modeling a discriminative feature space in IFSL for separating the base and the novel classes, we propose a feature augmentation strategy where the visual embeddings are supplemented with the semantic features obtained from a word-embedding space. Such a feature space is found to produce enriched class pro-totypes to be utilized during classification. Experimental results on CIFAR-100, CUB, mini-ImageNet, and tiered-ImageNet in the homogeneous (within-dataset) and a novel heterogeneous (cross-dataset) setup showcase sharp improvements than the literature.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Jaya Kalla
- Soma Biswas
- Aishwarya Agarwal
- Fabio Cuzzolin
- Biplab Banerjee
- Subhasis Chaudhuri
- Liyuan Wang
Citations in the corpus
- S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning (2023, methodology): “To better capture this performance balance, inspired from [39], recent FSCIL works [4,9] propose to use the Harmonic Mean (HM) of the performance of the previous and new classes at the end of each incremental task.”
- Semantics-Driven Generative Replay for Few-Shot Class Incremental Learning (2022, background): “We would like to point out that there exists another related problem setup called incremental few-shot learning (IFSL) [2, 26] which aims at maintaining comparable performance measures for the base and few-shot classes within a typical few-shot learning scenario.”