Browse State-of-the-Art › Fine-Grained Image Classification
Fine-Grained Image Classification
200 papers with code · 36 benchmarks · 41 datasets archive 2025-07-28
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.
( Image credit: Looking for the Devil in the Details )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
36 leaderboard tables shown for this task, 36 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 36 until expanded.
Syntology 18 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): Stanford Cars (1 judged, 0 placed), FGVC Aircraft (2 judged, 0 placed), CUB-200-2011 (2 judged, 1 placed), Oxford 102 Flowers (11 judged, 0 placed), Oxford-IIIT Pets (2 judged, 0 placed), Caltech-101 (1 judged, 0 placed), Food-101 (8 judged, 0 placed), SUN397 (3 judged, 0 placed), MNIST (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).
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
41 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 41 until expanded.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 353 · with a code link: 200 · where Syntology ran a sample: 54 (48 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (54 of 353 tagged: 48 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)
Page 1 of 4: papers 1 to 100 of 353, 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.
-
28 May 2019 144 repositories listed Syntology 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 (of 302 harvested samples) · 113 pointer-only (licence)Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available.
-
23 Dec 2020 40 repositories listed Syntology community repositories only · 12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified (of 19 harvested samples) · 3 pointer-only (licence)In this work, we produce a competitive convolution-free transformer by training on Imagenet only.
-
24 May 2018 33 repositories listed Syntology 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 (of 43 harvested samples) · 4 pointer-only (licence)In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch.
-
14 Apr 2023 26 repositories listed Syntology community repositories only · 39 ran (of which 13 constructed an object rather than computing a result; 32 with no instrument failure: 2 honoured, 0 violated, 30 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified (of 46 harvested samples) · 12 pointer-only (licence)The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.
-
7 May 2021 19 repositories listed Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples)We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification.
-
3 Oct 2020 18 repositories listed Syntology 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 (of 20 harvested samples) · 6 pointer-only (licence)In today's heavily overparameterized models, the value of the training loss provides few guarantees on model generalization ability.
-
1 Oct 2021 14 repositories listed Syntology official: harvested for another paper · 0 ran · 3 unverified (of 3 harvested samples)We share competitive training settings and pre-trained models in the timm open-source library, with the hope that they will serve as better baselines for future work.
-
16 Nov 2018 13 repositories listed Syntology 20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 25 harvested samples) · 16 pointer-only (licence)Scaling up deep neural network capacity has been known as an effective approach to improving model quality for several different machine learning tasks.
-
27 Feb 2021 12 repositories listed Syntology official (archive's flag): 4 ran · 16 ran (of which 12 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified (of 24 harvested samples) · 5 pointer-only (licence)In this paper, we point out that the attention inside these local patches are also essential for building visual transformers with high performance and we explore a new architecture, namely, Transformer iN Transformer…
-
2 Sep 2018 12 repositories listed Syntology 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 (of 9 harvested samples) · 3 pointer-only (licence)In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative…
-
12 Apr 2021 9 repositories listed Syntology community repositories only · 3 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; 2 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples) · 1 pointer-only (licence)Our models are flexible in terms of model size, and can have as little as 0.
-
24 Dec 2019 9 repositories listed Syntology community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples)We conduct detailed analysis of the main components that lead to high transfer performance.
-
18 Mar 2022 8 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)(2) Fine-tuning the weights of the attention layers is sufficient to adapt vision transformers to a higher resolution and to other classification tasks.
-
3 Apr 2020 8 repositories listed Syntology community repositories only · 18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified (of 29 harvested samples) · 3 pointer-only (licence)It has been shown that using the first and second order statistics (e. g., mean and variance) to perform Z-score standardization on network activations or weight vectors, such as batch normalization (BN) and weight…
-
26 Jan 2017 8 repositories listedWe verify the proposed method on a practical problem: person re-identification (re-ID).
-
20 Mar 2020 6 repositories listedTherefore, our multi-branch and multi-scale learning network(MMAL-Net) has good classification ability and robustness for images of different scales.
-
22 Apr 2021 5 repositories listed Syntology official (archive's flag): 1 ran · 1 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; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)ImageNet-1K serves as the primary dataset for pretraining deep learning models for computer vision tasks.
-
11 Feb 2021 5 repositories listed Syntology 8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples) · 9 pointer-only (licence)In this paper, we leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset.
-
8 Mar 2020 5 repositories listed Syntology 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 (of 6 harvested samples)In this work, we propose a novel framework for fine-grained visual classification to tackle these problems.
-
28 Mar 2023 4 repositories listed Syntology 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 (of 2 harvested samples) · 1 pointer-only (licence)Our generative approach to classification, which we call Diffusion Classifier, attains strong results on a variety of benchmarks and outperforms alternative methods of extracting knowledge from diffusion models.
-
29 Apr 2021 4 repositories listed Syntology 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 (of 5 harvested samples)On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53.
-
12 Jun 2019 4 repositories listed Syntology 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) · 3 unverified (of 5 harvested samples)Appearance information alone is often not sufficient to accurately differentiate between fine-grained visual categories.
-
26 Jan 2019 4 repositories listedSpecifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning.
-
4 Dec 2017 4 repositories listed Syntology 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 (of 3 harvested samples) · 1 pointer-only (licence)Towards addressing this problem, we propose an iterative matrix square root normalization method for fast end-to-end training of global covariance pooling networks.
-
29 Apr 2015 4 repositories listedWe then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also…
-
28 Mar 2024 3 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)This paper revives Densely Connected Convolutional Networks (DenseNets) and reveals the underrated effectiveness over predominant ResNet-style architectures.
-
7 Jul 2020 3 repositories listedTraditional learning with ImageNet pre-trained initial weights and SpinalNet classification layers provided the SOTA performance on STL-10, Fruits 360, Bird225, and Caltech-101 datasets.
-
31 Mar 2020 3 repositories listedThe former class can leverage fine-grained semantic relations between data points, but slows convergence in general due to its high training complexity.
-
30 Mar 2020 3 repositories listedIn this work, we introduce a series of architecture modifications that aim to boost neural networks' accuracy, while retaining their GPU training and inference efficiency.
-
11 Feb 2020 3 repositories listed Syntology 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 (of 5 harvested samples) · 2 pointer-only (licence)The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component.
-
16 Jan 2020 3 repositories listed
-
14 Jun 2019 3 repositories listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
1 Oct 2017 3 repositories listed
-
30 Jun 2015 3 repositories listed
-
25 Aug 2023 2 repositories listed
-
5 May 2023 2 repositories listed
-
23 Mar 2023 2 repositories listed
-
22 Mar 2023 2 repositories listed
-
6 Jan 2023 2 repositories listed
-
15 Mar 2022 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
5 Mar 2022 2 repositories listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 14 harvested samples) · 3 pointer-only (licence)
-
7 Feb 2022 2 repositories listed 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: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
20 Jan 2022 2 repositories listed
-
1 Jan 2022 2 repositories listed
-
14 Oct 2021 2 repositories listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 15 harvested samples) · 4 pointer-only (licence)
-
1 Jul 2021 2 repositories listed
-
3 Jun 2021 2 repositories listed
-
14 Mar 2021 2 repositories listed Syntology official (archive's flag): 1 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 2 pointer-only (licence)
-
31 Jan 2021 2 repositories listed
-
9 Dec 2020 2 repositories listed
-
14 Jul 2020 2 repositories listed Syntology community repositories only · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result (of 3 harvested samples) · 3 pointer-only (licence)
-
24 Jun 2020 2 repositories listed
-
12 May 2020 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
31 Mar 2020 2 repositories listed
-
14 Jan 2020 2 repositories listed
-
25 Sep 2019 2 repositories listed
-
16 Sep 2019 2 repositories listed
-
1 Jun 2019 2 repositories listed
-
30 Sep 2014 2 repositories listed
-
25 Jun 2025 1 repository listed
-
29 Apr 2025 1 repository listed
-
3 Mar 2025 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 7 harvested samples)
-
28 Jan 2025 1 repository listed
-
16 Jan 2025 1 repository listed Syntology 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)
-
6 Jan 2025 1 repository listed
-
27 Nov 2024 1 repository listed
-
20 Oct 2024 1 repository listed
-
17 Oct 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified (of 11 harvested samples)
-
9 Oct 2024 1 repository listed
-
28 Aug 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
25 Aug 2024 1 repository listed
-
16 Aug 2024 1 repository listed
-
13 Aug 2024 1 repository listed
-
13 Aug 2024 1 repository listed
-
5 Jul 2024 1 repository listed
-
5 Jul 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
28 Jun 2024 1 repository listed
-
20 Jun 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
13 Jun 2024 1 repository listed Syntology official (archive's flag): 17 ran · 17 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 6 honoured, 2 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified (of 22 harvested samples) · 6 pointer-only (licence)
-
3 Jun 2024 1 repository listed
-
12 Mar 2024 1 repository listed
-
1 Mar 2024 1 repository listed
-
25 Jan 2024 1 repository listed
-
4 Jan 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 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; 5 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
30 Dec 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 3 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
19 Dec 2023 1 repository listed
-
8 Dec 2023 1 repository listed
-
4 Dec 2023 1 repository listed
-
1 Dec 2023 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 16 harvested samples) · 10 pointer-only (licence)
-
29 Nov 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 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; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
7 Nov 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 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; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
29 Oct 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
20 Oct 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
18 Sep 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 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; 4 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples) · 8 pointer-only (licence)
-
23 Aug 2023 1 repository listed
-
8 Aug 2023 1 repository listed
-
28 Jul 2023 1 repository listed
-
21 Jul 2023 1 repository listed
-
17 Jul 2023 1 repository listed
-
24 May 2023 1 repository listed
Syntology lines on 46 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