Browse › Computer Vision › Fine-Grained Image Classification › FGVC Aircraft

Fine-Grained Image Classification archive 2025-07-28

FGVC Aircraft Benchmark (Fine-Grained Image Classification)

57 rows 42 with code listed 5 metrics Dataset page

Syntology Since the archive (Syntology): none placed; 2 newer papers judged to report on this board so far.

Fine-Grained Image Classification is a task in computer vision where the goal is to classify images into subcategories within a larger category. For example, classifying different species of birds or different types of flowers. This task is considered to be fine-grained because it requires the model to distinguish between subtle differences in visual appearance and patterns, making it more challenging than regular image classification tasks.

The archive carries no text for this table; the description above is the archive's text for the task Fine-Grained Image Classification. archive 2025-07-28

Over time archive 2025-07-28

Direction inferred from the metric name, not from the archive: Accuracy (higher is better), FLOPS (lower is better), PARAMS (lower is better), Top-1 (higher is better). Not inferred (points only, no best-so-far line): Top-1 Error Rate. Points are placed at the row's paper date, not an evaluation date; 56 of 57 rows carry one.

The chart needs JavaScript; the table below carries every value.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 I2-HOFI 96.42% – Paper Code 2024 linked, not harvested report
2 SR-GNN 95.49.830.9 – Paper Code 2022 linked, not harvested report
3 Inceptionv4 95.11 – Paper Code 2021 linked, not harvested report
4 CAP 94.9%34.2 – Paper Code 2021 0 ran · 2 unverified report
5 TBMSL-Net 94.7% – Paper Code 2020 linked, not harvested report
6 CMAL-Net 94.7% ✓ Paper Code 2023 linked, not harvested report
7 CSQA-Net 94.7% – Paper – 2024 no code linked report
8 PART 94.6% – Paper Code 2022 linked, not harvested report
9 AENet 94.5% – Paper – 2021 no code linked report
10 SaSPA + CAL 94.5 – Paper Code 2024 official: harvested, nothing ran · 0 ran · 1 unverified report
11 CAL 94.2 – Paper Code 2021 official (archive's flag): 8 ran · 8 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified report
12 CGL 94.2% – Paper Code 2025 linked, not harvested report
13 AttNet & AffNet 94.1% – Paper – 2020 no code linked report
14 CCFR 94.1% – Paper – 2021 no code linked report
15 DenseNet161+MM+FRL 94.0 % – Paper – 2020 no code linked report
16 API-Net 93.9% – Paper Code 2020 1 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; 0 where Syntology's instrument failed) · 1 unverified report
17 DF-GMM 93.8% – Paper – 2020 no code linked report
18 CMN 93.8% – – – not matched report
19 Multi Granularity 93.6% – Paper Code 2020 linked, not harvested report
20 DB 93.5% – Paper – 2019 no code linked report
21 BCN 93.5% – Paper – 2019 no code linked report
22 ELoPE 93.5% – Paper Code 2019 linked, not harvested report
23 SEB+EfficientNet-B5 93.5 – Paper Code 2022 official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified report
24 Grad-CAM 93.42% – Paper – 2021 no code linked report
25 PMG 93.4% – Paper Code 2020 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified report
26 CIN 93.3% – Paper – 2020 no code linked report
27 DCAL 93.3% – Paper – 2022 no code linked report
28 GCL 93.2% – Paper – 2020 no code linked report
29 Mix+ 93.1% – Paper Code 2020 linked, not harvested report
30 ViT-SAC 93.1% – Paper Code 2022 linked, not harvested report
31 WS-DAN 93.0% – Paper Code 2019 linked, not harvested report
32 MC Loss (B-CNN) 92.9% – Paper Code 2020 official (archive's flag): 2 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified report
33 EfficientNet-B7 92.9 – Paper Code 2019 official: no sample here; runs from other or unrecorded repositories · 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified report
34 MHEM (strong ResNet50 baseline) 92.9% – Paper Code 2022 linked, not harvested report
35 S3N 92.8% – Paper Code 2019 linked, not harvested report
36 PCA 92.8% – Paper Code 2021 linked, not harvested report
37 Cross-X 92.7% – Paper – 2019 no code linked report
38 LIO/ResNet-50 (multi-stage) 92.7% – Paper Code 2020 linked, not harvested report
39 ELP 92.7 – Paper Code 2022 linked, not harvested report
40 AutoAugment 92.67%7.33 – Paper Code 2018 community repositories only · 25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified report
41 Assemble-ResNet-FGVC-50 92.4 – Paper Code 2020 official (archive's flag): 3 ran · 3 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; 1 where Syntology's instrument failed) · 8 unverified report
42 ACNet 92.4% – Paper Code 2019 linked, not harvested report
43 SEF 92.1% – Paper Code 2020 linked, not harvested report
44 DFB-CNN 92.0% – Paper Code 2016 linked, not harvested report
45 MPN-COV 91.4% – Paper Code 2017 official (archive's flag): 2 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
46 NTS-Net (K=4) 91.4% – Paper Code 2018 official (archive's flag): 6 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
47 NAT-M4 90.8%581M5.3M – Paper Code 2020 official: harvested, nothing ran · 0 ran · 1 unverified report
48 NAT-M3 90.1%388M5.1M – Paper Code 2020 official: harvested, nothing ran · 0 ran · 1 unverified report
49 MACNN 89.9 – Paper Code 2017 linked, not harvested report
50 NAT-M2 89.0%235M3.4M – Paper Code 2020 official: harvested, nothing ran · 0 ran · 1 unverified report
51 BYOL+CVSA (ResNet-50) 87.27 – Paper Code 2021 linked, not harvested report
52 NAT-M1 87.0%175M3.2M – Paper Code 2020 official: harvested, nothing ran · 0 ran · 1 unverified report
53 NNCLR 64.1 – Paper Code 2021 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result report
54 SEER (RegNet10B) 54.82% ✓ Paper Code 2022 linked, not harvested report
55 Diffusion Classifier (zero-shot) 26.4 – Paper Code 2023 official (archive's flag): 1 ran · 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) · 0 unverified report
56 EffNet-L2 (SAM) 4.82 ✓ Paper Code 2020 official (archive's flag): 7 ran · 15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified report
57 ImageNet + iNat on WS-DAN 91.5 – Paper – 2020 no code linked report

All 57 rows shown. 56 link to a paper page on this site; 3 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran 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”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 19 rows have a graph line, from 16 distinct papers. Rows whose paper has a sample that ran: 13 (12 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument). Papers: 13 with a sample that ran: 12 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 19 rows with a graph line, 16 have an archive-official repository: on 9 a sample from it ran (8 with a run with no instrument failure), on 1 the samples that ran came from community repositories only, and on 1 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 440 samples: 287 ran (of which 90 constructed an object rather than computing a result; 227 with no instrument failure: 30 honoured, 4 violated, 193 with no contract checked; 60 where Syntology's instrument failed) · 153 unverified. Separately, 134 of those 440 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive Syntology

Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 8 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,589 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 2 proposed a result; of those 2, 2 were rejected by the independent check, 0 await a verdict and 0 were placed. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.

Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)

Paper arXiv date Ran Syntology Outcome
FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration arXiv:2606.28654 26 Jun 2026 4 harvested: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified rejected by the independent check
Bio-inspired fine-tuning for selective transfer learning in image classification arXiv:2601.11235 16 Jan 2026 3 harvested: 2 ran (of which 2 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) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result rejected by the independent check

Syntology 2 newer papers judged to report on this board: the papers counted above as having proposed a result (0 placed); every one is listed here and in the JSON twin. The order is the arXiv identifier's, newest first, not a rank. The judgement is the model's, read from the paper's own tables; the outcome is what Syntology's checks did with it, and no value from a paper that was not placed is printed. “refused by a rule” names the extractor's rule; “no cell passed the extractor's checks” means the extractor's record holds no cell for this board, passed or refused. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

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