Papers › Compositional Few-Shot Class-Incremental Learning

Compositional Few-Shot Class-Incremental Learning

27 May 2024arXiv:2405.17022archive 2025-07-28

Yixiong Zou, Shanghang Zhang, Haichen Zhou, Yuhua Li, Ruixuan Li

Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data. However, this remains a challenge. In contrast, humans can easily recognize novel classes with a few samples. Cognitive science demonstrates that an important component of such human capability is compositional learning. This involves identifying visual primitives from learned knowledge and then composing new concepts using these transferred primitives, making incremental learning both effective and interpretable. To imitate human compositional learning, we propose a cognitive-inspired method for the FSCIL task. We define and build a compositional model based on set similarities, and then equip it with a primitive composition module and a primitive reuse module. In the primitive composition module, we propose to utilize the Centered Kernel Alignment (CKA) similarity to approximate the similarity between primitive sets, allowing the training and evaluation based on primitive compositions. In the primitive reuse module, we enhance primitive reusability by classifying inputs based on primitives replaced with the closest primitives from other classes. Experiments on three datasets validate our method, showing it outperforms current state-of-the-art methods with improved interpretability. Our code is available at https://github.com/Zoilsen/Comp-FSCIL.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.17022")

Code

Syntology Ran 9 of 15 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 9 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zoilsen/comp-fscil officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 9 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
6ran
6unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zoilsen/comp-fscil. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv1x1 zoilsen/comp-fscil/models/resnet18_encoder.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv1x1 zoilsen/comp-fscil/models/resnet12.py official repository ran MIT (permissive) · de92832114f71d8c · report
conv3x3 zoilsen/comp-fscil/models/resnet18_encoder.py official repository ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report
conv3x3 zoilsen/comp-fscil/models/resnet20_cifar.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
conv3x3 zoilsen/comp-fscil/models/resnet12.py official repository ran MIT (permissive) · e5b7c79b0b62af96 · report
get_base_dataloader zoilsen/comp-fscil/dataloader/data_utils.py official repository ran MIT (permissive) · 3f0e2ea167ccd1bf · report
load_state_dict_from_url zoilsen/comp-fscil/models/resnet18_encoder.py official repository ran MIT (permissive) · 422a6083ee9c106d · report
norm_layer zoilsen/comp-fscil/models/resnet12.py official repository ran MIT (permissive) · f36ac42575cd46ee · report
set_gpu zoilsen/comp-fscil/utils.py official repository ran MIT (permissive) · 8327880f0b76f9db · report
base_train zoilsen/comp-fscil/models/base/helper.py official repository unverified MIT (permissive) · ddaa52a660b55402 · report
count_acc zoilsen/comp-fscil/utils.py official repository unverified MIT (permissive) · 684d8ecbca8220ab · report
get_dataloader zoilsen/comp-fscil/dataloader/data_utils.py official repository unverified MIT (permissive) · 91defe5d31d82cad · report
replace_base_fc zoilsen/comp-fscil/models/base/helper.py official repository unverified MIT (permissive) · fa6d7dbb6906a211 · report
set_up_datasets zoilsen/comp-fscil/dataloader/data_utils.py official repository unverified MIT (permissive) · dc5f16fd17d2ba25 · report
test zoilsen/comp-fscil/models/base/helper.py official repository unverified MIT (permissive) · 7e0029dd3479294e · report

Tasks

Class Incremental LearningFew-Shot Class-Incremental LearningIncremental Learningclass-incremental learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASESET

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