Papers › Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches

Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches

8 Mar 2020ECCV 2020 8arXiv:2003.03836archive 2025-07-28

Ruoyi Du, Dongliang Chang, Ayan Kumar Bhunia, Jiyang Xie, Zhanyu Ma, Yi-Zhe Song, Jun Guo

Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works mainly tackle this problem by focusing on how to locate the most discriminative parts, more complementary parts, and parts of various granularities. However, less effort has been placed to which granularities are the most discriminative and how to fuse information cross multi-granularity. In this work, we propose a novel framework for fine-grained visual classification to tackle these problems. In particular, we propose: (i) a progressive training strategy that effectively fuses features from different granularities, and (ii) a random jigsaw patch generator that encourages the network to learn features at specific granularities. We obtain state-of-the-art performances on several standard FGVC benchmark datasets, where the proposed method consistently outperforms existing methods or delivers competitive results. The code will be available at https://github.com/PRIS-CV/PMG-Progressive-Multi-Granularity-Training.

PaperPDFConference PDFCodeCode 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="2003.03836")

Code

Syntology Ran 2 of 6 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 6 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

PRIS-CV/PMG-Progressive-Multi-Granularity-Training officialmentioned in paperpytorchMIT report
RuoyiDu/PMG-Progressive-Multi-Granularity-Training officialmentioned in paperpytorchMIT report
kalelpark/FG-SSL mentioned on GitHubpytorch 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

6 samples harvested; 2 ran; 0 honoured the contract we drafted; 4 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
4unverified

Licence: 0 of the 6 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 PRIS-CV/PMG-Progressive-Multi-Granularity-Training. “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 PRIS-CV/PMG-Progressive-Multi-Granularity-Training/Resnet.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 PRIS-CV/PMG-Progressive-Multi-Granularity-Training/Resnet.py official repository ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report
cosine_anneal_schedule PRIS-CV/PMG-Progressive-Multi-Granularity-Training/utils.py official repository unverified MIT (permissive) · c47fe09ebc04c5c2 · report
jigsaw_generator PRIS-CV/PMG-Progressive-Multi-Granularity-Training/utils.py official repository unverified MIT (permissive) · e8b11864a40bbca9 · report
load_model PRIS-CV/PMG-Progressive-Multi-Granularity-Training/utils.py official repository unverified MIT (permissive) · e930d1ccdd527d08 · report
resnet18 PRIS-CV/PMG-Progressive-Multi-Granularity-Training/Resnet.py official repository unverified MIT (permissive) · 2899baee55d29ffb · report

Tasks

ClassificationFine-Grained Image ClassificationGeneral Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Image Classification FGVC Aircraft PMG Accuracy 93.4% #25 of 57 Archive leaderboard report
Fine-Grained Image Classification Stanford Cars PMG Accuracy 95.1% #21 of 83 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.

Methods

Jigsaw

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