# Generative Modeling on Sequential ImageNet (Cats), CUB 200, LSUN (Churches & Towers) Source: [Generative Modeling on Sequential ImageNet (Cats), CUB 200, LSUN (Churches & Towers)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:44:47.832Z Evaluation of generative models using average FID scores across four distinct image datasets: Sequential ImageNet (Cats), CUB 200 (Birds), LSUN (Churches), and LSUN (Towers). A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Generative Modeling | | Dataset (including any stated split) | Sequential ImageNet (Cats), CUB 200 (Birds), LSUN (Churches), LSUN (Towers) | | Metric | FID (Cats, Task 1) | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 4 of 4 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [FID (Cats, Task 1)](): Lower is better; unit: SCALAR. - [FID (Cats, Task 2)](): Lower is better; unit: SCALAR. - [FID (Cats, Task 3)](): Lower is better; unit: SCALAR. - [FID (Cats, Task 4)](): Lower is better; unit: SCALAR. - [FID (Birds, Task 1)](): Lower is better; unit: SCALAR. - [FID (Birds, Task 2)](): Lower is better; unit: SCALAR. - [FID (Birds, Task 3)](): Lower is better; unit: SCALAR. - [FID (Birds, Task 4)](): Lower is better; unit: SCALAR. - [FID (Churches, Task 1)](): Lower is better; unit: SCALAR. - [FID (Churches, Task 2)](): Lower is better; unit: SCALAR. - [FID (Churches, Task 3)](): Lower is better; unit: SCALAR. - [FID (Churches, Task 4)](): Lower is better; unit: SCALAR. - [FID (Towers, Task 1)](): Lower is better; unit: SCALAR. - [FID (Towers, Task 2)](): Lower is better; unit: SCALAR. - [FID (Towers, Task 3)](): Lower is better; unit: SCALAR. - [FID (Towers, Task 4)](): Lower is better; unit: SCALAR. - [Average FID (Overall)](): Lower is better; unit: SCALAR. ## Recorded results | Method | FID (Cats, Task 1) | Result date | Report paper | | --- | --- | --- | --- | | Finetune | 29 | Not recorded | 68fa69981e209131cea22ef0 | | EWC | 29 | Not recorded | 68fa69981e209131cea22ef0 | | MeRGAN-RA | 29 | Not recorded | 68fa69981e209131cea22ef0 | | EFT | 29 | Not recorded | 68fa69981e209131cea22ef0 | ### Finetune FID (Cats, Task 1): 29. Result ID: 698dbea08b517eb433237558. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### EWC FID (Cats, Task 1): 29. Result ID: 698dbea08b517eb433237559. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MeRGAN-RA FID (Cats, Task 1): 29. Result ID: 698dbea08b517eb43323755a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### EFT FID (Cats, Task 1): 29. Result ID: 698dbea08b517eb43323755b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"rank configuration":"a=32, b=16","parameter expansion":"+4.8%"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.