Semantic-visual Guided Transformer for Few-shot Class-incremental Learning

27 Mar 2023  ·  Wenhao Qiu, Sichao Fu, Jingyi Zhang, Chengxiang Lei, Qinmu Peng ·

Few-shot class-incremental learning (FSCIL) has recently attracted extensive attention in various areas. Existing FSCIL methods highly depend on the robustness of the feature backbone pre-trained on base classes. In recent years, different Transformer variants have obtained significant processes in the feature representation learning of massive fields. Nevertheless, the progress of the Transformer in FSCIL scenarios has not achieved the potential promised in other fields so far. In this paper, we develop a semantic-visual guided Transformer (SV-T) to enhance the feature extracting capacity of the pre-trained feature backbone on incremental classes. Specifically, we first utilize the visual (image) labels provided by the base classes to supervise the optimization of the Transformer. And then, a text encoder is introduced to automatically generate the corresponding semantic (text) labels for each image from the base classes. Finally, the constructed semantic labels are further applied to the Transformer for guiding its hyperparameters updating. Our SV-T can take full advantage of more supervision information from base classes and further enhance the training robustness of the feature backbone. More importantly, our SV-T is an independent method, which can directly apply to the existing FSCIL architectures for acquiring embeddings of various incremental classes. Extensive experiments on three benchmarks, two FSCIL architectures, and two Transformer variants show that our proposed SV-T obtains a significant improvement in comparison to the existing state-of-the-art FSCIL methods.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Class-Incremental Learning CIFAR-100 SV-T Average Accuracy 76.84 # 1
Last Accuracy 69.75 # 1
Few-Shot Class-Incremental Learning CUB-200-2011 SV-T Average Accuracy 78.65 # 1
Last Accuracy 76.17 # 1
Few-Shot Class-Incremental Learning mini-Imagenet SV-T Average Accuracy 85.07 # 1
Last Accuracy 81.65 # 1

Methods