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

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

27 Mar 2023arXiv:2303.15494archive 2025-07-28

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.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Class Incremental Learning Few-Shot Class-Incremental Learning Incremental Learning Representation Learning class-incremental learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Few-Shot Class-Incremental Learning	CIFAR-100	SV-T	Average Accuracy	76.84	#3 of 11	Archive leaderboard	report
Few-Shot Class-Incremental Learning	CIFAR-100	SV-T	Last Accuracy	69.75	#3 of 11	Archive leaderboard	report
Few-Shot Class-Incremental Learning	CUB-200-2011	SV-T	Average Accuracy	78.65	#3 of 6	Archive leaderboard	report
Few-Shot Class-Incremental Learning	CUB-200-2011	SV-T	Last Accuracy	76.17	#3 of 6	Archive leaderboard	report
Few-Shot Class-Incremental Learning	mini-Imagenet	SV-T	Average Accuracy	85.07	#3 of 12	Archive leaderboard	report
Few-Shot Class-Incremental Learning	mini-Imagenet	SV-T	Last Accuracy	81.65	#3 of 12	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BASE BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections