Few-Shot Object Detection

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

10 leaderboard tables shown for this task, 10 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.

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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

8 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 97 papers with code (179 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
  19 Apr 2022 9 repositories listed Syntology ran 4 of 20 samples · 16 unverified
  In general, these language-augmented visual models demonstrate strong transferability to a variety of datasets and tasks.
• Frustratingly Simple Few-Shot Object Detection
  16 Mar 2020 5 repositories listed Syntology ran 3 of 11 samples · 8 unverified · 11 pointer-only (licence)
  Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods.
• NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
  14 Apr 2025 4 repositories listed
  Cross-Domain Few-Shot Object Detection (CD-FSOD) poses significant challenges to existing object detection and few-shot detection models when applied across domains.
• Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
  8 Mar 2021 4 repositories listed Syntology ran 3 of 6 samples · 3 unverified · 6 pointer-only (licence)
  Few-shot object detection has made substantial progressby representing novel class objects using the feature representation learned upon a set of base class objects.
• Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
  18 Jul 2020 4 repositories listed Syntology ran 5 of 8 samples · 3 unverified
  Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited.
• Few-shot Object Detection via Feature Reweighting
  5 Dec 2018 4 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples.
• Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection
  16 May 2024 3 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  Empirical results demonstrate the effectiveness of Grounding DINO 1.
• Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
  19 May 2022 3 repositories listed
  Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models.
• Grounded Language-Image Pre-training
  7 Dec 2021 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  The unification brings two benefits: 1) it allows GLIP to learn from both detection and grounding data to improve both tasks and bootstrap a good grounding model; 2) GLIP can leverage massive image-text pairs by…
• Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
  6 Aug 2019 3 repositories listed Syntology ran 2 of 10 samples · 8 unverified
  To train our network, we contribute a new dataset that contains 1000 categories of various objects with high-quality annotations.
• One-Shot Instance Segmentation
  28 Nov 2018 3 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection…
• No time to train! Training-Free Reference-Based Instance Segmentation
  3 Jul 2025 2 repositories listed
  The performance of image segmentation models has historically been constrained by the high cost of collecting large-scale annotated data.
• Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector
  5 Feb 2024 2 repositories listed Syntology ran 9 of 11 samples · 2 unverified
  This paper studies the challenging cross-domain few-shot object detection (CD-FSOD), aiming to develop an accurate object detector for novel domains with minimal labeled examples.
• Mobile Robot Manipulation using Pure Object Detection
  28 Jan 2022 2 repositories listed
  We develop an end-to-end manipulation method based solely on detection and introduce Task-focused Few-shot Object Detection (TFOD) to learn new objects and settings.
• DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
  20 Aug 2021 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  Few-shot object detection, which aims at detecting novel objects rapidly from extremely few annotated examples of previously unseen classes, has attracted significant research interest in the community.
• Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment
  15 Apr 2021 2 repositories listed
  To improve the fine-grained few-shot proposal classification, we propose a novel attentive feature alignment method to address the spatial misalignment between the noisy proposals and few-shot classes, thus improving…
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
  22 Mar 2021 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks.
• FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
  10 Mar 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected…
• Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
  23 Jul 2020 2 repositories listed Syntology ran 1 of 17 samples · 16 unverified
  In this paper, we tackle the problems of few-shot object detection and few-shot viewpoint estimation.
• Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
  20 May 2025 1 repository listed Syntology ran 4 of 7 samples · 3 unverified
  This paper focus on few-shot object detection~(FSOD) and instance segmentation~(FSIS), which requires a model to quickly adapt to novel classes with a few labeled instances.
• CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion
  2 May 2025 1 repository listed
  Cross-domain few-shot object detection (CD-FSOD) aims to detect novel objects across different domains with limited class instances.
• Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection
  9 Apr 2025 1 repository listed
  The core challenge of this task is how to construct a generalized feature space for novel categories with limited data on the basis of the base category space, which could adapt the learned detection model to unknown…
• Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection
  6 Apr 2025 1 repository listed
  Foundation models pretrained on extensive datasets, such as GroundingDINO and LAE-DINO, have performed remarkably in the cross-domain few-shot object detection (CD-FSOD) task.
• Visual-RFT: Visual Reinforcement Fine-Tuning
  3 Mar 2025 1 repository listed Syntology ran 0 of 7 samples · 7 unverified
  Reinforcement Fine-Tuning (RFT) in Large Reasoning Models like OpenAI o1 learns from feedback on its answers, which is especially useful in applications when fine-tuning data is scarce.
• Multi-Perspective Data Augmentation for Few-shot Object Detection
  25 Feb 2025 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Recent few-shot object detection (FSOD) methods have focused on augmenting synthetic samples for novel classes, show promising results to the rise of diffusion models.
• Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichment
  23 Feb 2025 1 repository listed
  Advancements in cross-modal feature extraction and integration have significantly enhanced performance in few-shot learning tasks.
• Generalization-Enhanced Few-Shot Object Detection in Remote Sensing
  5 Jan 2025 1 repository listed
  However, the generalization capability of FSOD models, particularly in remote sensing, is often constrained by the complex and diverse characteristics of the objects present in such environments.
• SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection
  28 Dec 2024 1 repository listed
  Recent years have witnessed tremendous advances on modern visual recognition systems.
• Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability
  20 Oct 2024 1 repository listed
  Our findings reveal that: i) there is little difference between OVD and COD for object classes with low text-describability under equal conditions in OD pretraining; and ii) although OVD can learn from more diverse data…
• PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection
  11 Aug 2024 1 repository listed
  Specifically, we design a Test-Time Learning (TTL) module that employs a mean-teacher network for self-training to discover novel instances from test data, allowing detectors to learn better representations and…

Syntology lines on 17 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. Read from the graph 2026-09-24.