Browse State-of-the-Art › Incremental Learning

Incremental Learning

542 papers with code · 22 benchmarks · 8 datasets archive 2025-07-28

Methodology

Incremental learning aims to develop artificially intelligent systems that can continuously learn to address new tasks from new data while preserving knowledge learned from previously learned tasks.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

22 leaderboard tables shown for this task, 22 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 22 until expanded.

Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): CIFAR-100 - 50 classes + 5 steps of 10 classes (1 judged, 0 placed), CIFAR-100 - 50 classes + 10 steps of 5 classes (1 judged, 0 placed), CIFAR-100 - 50 classes + 25 steps of 2 classes (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
CIFAR-100 - 50 classes + 5 steps of 10 classes (15 rows) TCIL Resolving Task Confusion in Dynamic Expansion Architectures for... code — Compare
CIFAR-100 - 50 classes + 10 steps of 5 classes (13 rows) TCIL Resolving Task Confusion in Dynamic Expansion Architectures for... code — Compare
ImageNet100 - 10 steps (13 rows) kNN-CLIP Revisiting a kNN-based Image Classification System with... — — Compare
CIFAR-100-B0(5steps of 20 classes) (10 rows) View-Batch(TCIL) Do Your Best and Get Enough Rest for Continual Learning code — Compare
ImageNet - 10 steps (10 rows) kNN-CLIP Revisiting a kNN-based Image Classification System with... — — Compare
CIFAR100-B0(10steps of 10 classes) (6 rows) View-Batch(DER) Do Your Best and Get Enough Rest for Continual Learning code — Compare
CIFAR-100 - 50 classes + 25 steps of 2 classes (5 rows) D3Former D3Former: Debiased Dual Distilled Transformer for Incremental Learning code — Compare
CIFAR100B020Step(5ClassesPerStep) (5 rows) View-Batch(DER) Do Your Best and Get Enough Rest for Continual Learning code — Compare
ImageNet-100 - 50 classes + 10 steps of 5 classes (5 rows) RMM (ResNet-18) RMM: Reinforced Memory Management for Class-Incremental Learning code Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
ImageNet-100 - 50 classes + 5 steps of 10 classes (5 rows) FOSTER FOSTER: Feature Boosting and Compression for Class-Incremental Learning code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified Compare
CIFAR-100 - 50 classes + 2 steps of 25 classes (4 rows) TCIL Resolving Task Confusion in Dynamic Expansion Architectures for... code — Compare
ImageNet - 500 classes + 5 steps of 100 classes (4 rows) RMM (ResNet-18) RMM: Reinforced Memory Management for Class-Incremental Learning code Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
ImageNet - 500 classes + 10 steps of 50 classes (4 rows) RMM (ResNet-18) RMM: Reinforced Memory Management for Class-Incremental Learning code Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
ImageNet-100 - 50 classes + 25 steps of 2 classes (3 rows) RMM (ResNet-18) RMM: Reinforced Memory Management for Class-Incremental Learning code Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
CIFAR-100 - 50 classes + 50 steps of 1 class (2 rows) PODNet PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning code — Compare
ImageNet-100 - 50 classes + 50 steps of 1 class (2 rows) PODNet PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning code — Compare
CIFAR-100 - 40 classes + 60 steps of 1 class (Exemplar-free) (1 row) FeTrIL FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning code — Compare
CIFAR100B050S(2ClassesPerStep) (1 row) DER(ResNet-18) DER: Dynamically Expandable Representation for Class Incremental Learning code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified Compare
ImageNet-10k - 5225 classes + 5 steps of 1045 classes (1 row) PPCA-CLIP Scalable Learning with Incremental Probabilistic PCA code — Compare
ImageNet - 500 classes + 25 steps of 20 classes (1 row) RMM (ResNet-18) RMM: Reinforced Memory Management for Class-Incremental Learning code Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
ImageNet100 - 20 steps (1 row) FOSTER FOSTER: Feature Boosting and Compression for Class-Incremental Learning code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified Compare
MLT17 (1 row) MRM MRN: Multiplexed Routing Network for Incremental Multilingual Text... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

8 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 1,371 · with a code link: 542 · where Syntology ran a sample: 162 (144 with a run with no instrument failure, 18 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (162 of 1,371 tagged: 144 with a run with no instrument failure, 18 where every run was a failure of Syntology's instrument)

Page 1 of 14: papers 1 to 100 of 1,371, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 40 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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