Browse State-of-the-Art › Long-tailed Object Detection
Long-tailed Object Detection
18 papers with code · 1 benchmark · 1 dataset archive 2025-07-28
The training dataset obeys a long-tailed distribution, i.e., the head categories occupy most samples whereas the tail categories only own a few samples. However, the testing dataset is balanced across categories.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| LVIS v1.0 val (1 row) | R101 Faster R-CNN | Balanced Classification: A Unified Framework for Long-Tailed... | code | — | Compare |
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
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 25 · with a code link: 18 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 25 tagged: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 25 of 25, 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.
-
15 Dec 2020 2 repositories listedTo address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process…
-
28 Dec 2024 1 repository listedRecent years have witnessed tremendous advances on modern visual recognition systems.
-
21 Nov 2024 1 repository listedDINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.
-
15 Oct 2024 1 repository listedFRACAL devises a logit adjustment method that utilises the fractal dimension to estimate how uniformly classes are distributed in image space.
-
10 Jan 2024 1 repository listedEnsemble methods exploit the availability of a given number of classifiers or detectors trained in single or multiple source domains and tasks to address machine learning problems such as domain adaptation or…
-
18 Oct 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 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; 2 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 7 pointer-only (licence)Specifically, we add a semantic branch to our detector to learn these soft semantics and enhance feature representations for long-tailed object detection.
-
4 Aug 2023 1 repository listedIn this paper, we contend that the learning bias originates from two factors: 1) the unequal competition arising from the imbalanced distribution of foreground categories, and 2) the lack of sample diversity in tail…
-
24 May 2023 1 repository listedThis paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature.
-
23 Jan 2023 1 repository listedLarge-scale object detection and instance segmentation face a severe data imbalance.
-
17 Nov 2022 1 repository listedIt has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.
-
11 Oct 2022 1 repository listedSpecifically, there are an object detection task (consisting of an instance-classification task and a localization task) and an image-classification task in our framework, responsible for utilizing the two types of…
-
11 Oct 2022 1 repository listedLong-tail distribution is widely spread in real-world applications.
-
7 Jan 2022 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) · 0 unverified (of 3 harvested samples)The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem.
-
17 Aug 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)Specifically, EBL increases the intensity of the adjustment of the decision boundary for the weak classes by a designed score-guided loss margin between any two classes.
-
5 Jul 2021 1 repository listedWe propose NorCal, Normalized Calibration for long-tailed object detection and instance segmentation, a simple and straightforward recipe that reweighs the predicted scores of each class by its training sample size.
-
17 Feb 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Many objects do not appear frequently enough in complex scenes (e. g., certain handbags in living rooms) for training an accurate object detector, but are often found frequently by themselves (e. g., in product images).
-
7 Nov 2020 1 repository listedTo this end, we rethink long-tailed object detection in UAV images and propose the Dual Sampler and Head detection Network (DSHNet), which is the first work that aims to resolve long-tail distribution in UAV images.
-
13 Aug 2020 1 repository listedIn the classification tree, as the number of parent class nodes are significantly less, their logits are less noisy and can be utilized to suppress the wrong/noisy logits existed in the fine-grained class nodes.
-
Exponentially Weighted Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection Model Training in Unmanned Aerial Vehicles Surveillance Scenarios27 Mar 2025 0 repositories listedObject detection models often struggle with class imbalance, where rare categories appear significantly less frequently than common ones.
-
Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount6 Feb 2025 0 repositories listedIn object detection, the instance count is typically used to define whether a dataset exhibits a long-tail distribution, implicitly assuming that models will underperform on categories with fewer instances.
-
Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction14 Nov 2024 0 repositories listedPre-training plays a vital role in various vision tasks, such as object recognition and detection.
-
Rectify the Regression Bias in Long-Tailed Object Detection29 Jan 2024 0 repositories listedLong-tailed object detection faces great challenges because of its extremely imbalanced class distribution.
-
Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data22 May 2023 0 repositories listedReal-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training.
-
Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection14 May 2023 0 repositories listedWe propose an embarrassingly simple method -- instance-aware repeat factor sampling (IRFS) to address the problem of imbalanced data in long-tailed object detection.
-
Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection1 Jan 2022 0 repositories listedGeneral object detectors are always evaluated on hand-designed datasets, e.g., MS COCO and Pascal VOC, which tend to maintain balanced data distribution over different classes.
Syntology lines on 4 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