Papers › On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition

On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition

26 May 2022arXiv:2205.13282archive 2025-07-28

Yue Song, Nicu Sebe, Wei Wang

The Fine-Grained Visual Categorization (FGVC) is challenging because the subtle inter-class variations are difficult to be captured. One notable research line uses the Global Covariance Pooling (GCP) layer to learn powerful representations with second-order statistics, which can effectively model inter-class differences. In our previous conference paper, we show that truncating small eigenvalues of the GCP covariance can attain smoother gradient and improve the performance on large-scale benchmarks. However, on fine-grained datasets, truncating the small eigenvalues would make the model fail to converge. This observation contradicts the common assumption that the small eigenvalues merely correspond to the noisy and unimportant information. Consequently, ignoring them should have little influence on the performance. To diagnose this peculiar behavior, we propose two attribution methods whose visualizations demonstrate that the seemingly unimportant small eigenvalues are crucial as they are in charge of extracting the discriminative class-specific features. Inspired by this observation, we propose a network branch dedicated to magnifying the importance of small eigenvalues. Without introducing any additional parameters, this branch simply amplifies the small eigenvalues and achieves state-of-the-art performances of GCP methods on three fine-grained benchmarks. Furthermore, the performance is also competitive against other FGVC approaches on larger datasets. Code is available at \href{https://github.com/KingJamesSong/DifferentiableSVD}{https://github.com/KingJamesSong/DifferentiableSVD}.

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="2205.13282")

Code

Syntology Ran 3 of 17 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

KingJamesSong/DifferentiableSVD officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

17 samples harvested; 3 ran; 0 honoured the contract we drafted; 14 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.

2ran · our draft was wrong
1ran
14unverified

Licence: 0 of the 17 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 KingJamesSong/DifferentiableSVD. “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 KingJamesSong/DifferentiableSVD/src/network/resnet.py official repository ran · our draft was wrong Apache-2.0 (permissive) · d9def42110729a85 · report
conv3x3 KingJamesSong/DifferentiableSVD/src/network/resnet.py official repository ran · our draft was wrong Apache-2.0 (permissive) · fac5364e2f53c6db · report
make_layers KingJamesSong/DifferentiableSVD/src/network/mpncovvgg.py official repository ran Apache-2.0 (permissive) · ac62432dc5134b0d · report
alexnet KingJamesSong/DifferentiableSVD/src/network/alexnet.py official repository unverified Apache-2.0 (permissive) · 2f5db20279adcab2 · report
center_crop_with_flip KingJamesSong/DifferentiableSVD/imagepreprocess.py official repository unverified Apache-2.0 (permissive) · e1bba953865399c4 · report
decode_params KingJamesSong/DifferentiableSVD/functions.py official repository unverified Apache-2.0 (permissive) · e9ae7b09751b4912 · report
densenet121 KingJamesSong/DifferentiableSVD/src/network/densenet.py official repository unverified Apache-2.0 (permissive) · 10d70cd9de88accd · report
densenet169 KingJamesSong/DifferentiableSVD/src/network/densenet.py official repository unverified Apache-2.0 (permissive) · 4983bf3da7e3bc95 · report
densenet201 KingJamesSong/DifferentiableSVD/src/network/densenet.py official repository unverified Apache-2.0 (permissive) · c26ebe510580f5fa · report
get_basemodel KingJamesSong/DifferentiableSVD/src/network/base.py official repository unverified Apache-2.0 (permissive) · b3aff4f65217439f · report
inception_v3 KingJamesSong/DifferentiableSVD/src/network/inception.py official repository unverified Apache-2.0 (permissive) · 99f547d08bd82760 · report
mpncovresnet101 KingJamesSong/DifferentiableSVD/src/network/mpncovresnet.py official repository unverified Apache-2.0 (permissive) · 821722d0a708c2b9 · report
mpncovresnet50 KingJamesSong/DifferentiableSVD/src/network/mpncovresnet.py official repository unverified Apache-2.0 (permissive) · da56958c53b9740c · report
preprocess_strategy KingJamesSong/DifferentiableSVD/imagepreprocess.py official repository unverified Apache-2.0 (permissive) · 7d5e18eb2768dd94 · report
resnet18 KingJamesSong/DifferentiableSVD/src/network/resnet.py official repository unverified Apache-2.0 (permissive) · bc9961dacb0c6e52 · report
vgg11 KingJamesSong/DifferentiableSVD/src/network/vgg.py official repository unverified Apache-2.0 (permissive) · 9ec7dbb47bd1938b · report
vgg11_bn KingJamesSong/DifferentiableSVD/src/network/vgg.py official repository unverified Apache-2.0 (permissive) · 57ac34428a02311d · report

Tasks

Fine-Grained Image ClassificationFine-Grained Visual CategorizationFine-Grained Visual RecognitionImage Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification FGVC Aircraft SEB+EfficientNet-B5 Accuracy 93.5 #23 of 57 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars SEB+EfficientNet-B5 Accuracy 94.6% #40 of 83 Archive leaderboard report
Fine-Grained Image Classification Stanford Dogs SEB+EfficientNet-B5 Accuracy 93.0% #7 of 24 Archive leaderboard report
Image Classification iNaturalist SEB+EfficientNet-B5 Top 1 Accuracy 72.3 #12 of 19 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.

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