/awesome-few-shot-object-detection

Collect some papers and datastes about few-shot object detection for computer vision.

Awesome-Few-Shot-Object-Detection

Collect some papers about few-shot object detection for computer vision. Additionally, we briefly introduce the commonly used datasets for few-shot object detection.

Papers

Survey

Title Venue PDF
A Survey of Deep Learning for Low-Shot Object Detection ArXiv 2022 PDF
A Unified Framework for Attention-Based Few-Shot Object Detection ArXiv 2022 PDF

2023

Title Venue Dataset PDF CODE
FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training ICCV 2023 PASCAL VOC & MS COCO PDF -
σ-Adaptive Decoupled Prototype for Few-Shot Object Detection ICCV 2023 PASCAL VOC & MS COCO & FSOD PDF -
Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection CVPR 2023 PASCAL VOC & MS COCO PDF -
Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection CVPR 2023 PASCAL VOC & MS COCO PDF -
NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forging CVPR 2023 PASCAL VOC & MS COCO PDF -
DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection CVPR 2023 PASCAL VOC & MS COCO & LVIS PDF -
Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection AAAI 2023 PASCAL VOC & MS COCO PDF CODE
Few-Shot Object Detection via Variational Feature Aggregation AAAI 2023 PASCAL VOC & MS COCO PDF CODE
Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective AAAI 2023 PASCAL VOC & MS COCO PDF CODE

2022

Title Venue Dataset PDF CODE
Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark ECCV 2022 LVIS & MS COCO PDF -
AirDet: Few-Shot Detection without Fine-Tuning for Autonomous Exploration ECCV 2022 PASCAL VOC & MS COCO PDF CODE
Less than Few: Self-Shot Video Instance Segmentation ECCV 2022 MS COCO PDF -
Time-rEversed diffusioN tEnsor Transformer: A New TENET of Few-Shot Object Detection ECCV 2022 PASCAL VOC & MS COCO & FSOD PDF CODE
VizWiz-FewShot: Locating Objects in Images Taken by People with Visual Impairments ECCV 2022 PASCAL VOC & MS COCO PDF CODE
Multi-faceted Distillation of Base-Novel Commonality for Few-Shot Object Detection ECCV 2022 PASCAL VOC & MS COCO PDF CODE
Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations ECCV 2022 PASCAL VOC & MS COCO PDF -
Few-Shot Object Detection with Model Calibration ECCV 2022 PASCAL VOC & MS COCO PDF CODE
Few-Shot Video Object Detectio ECCV 2022 FSVOD-500 PDF CODE
Few-Shot Object Counting and Detection ECCV 2022 FSCD-147 & FSCD-LVIS PDF CODE
Mutually Reinforcing Structure with Proposal Contrastive Consistency for Few-Shot Object Detection ECCV 2022 PASCAL VOC & MS COCO PDF CODE
Few-Shot End-to-End Object Detection via Constantly Concentrated Encoding across Heads ECCV 2022 PASCAL VOC & MS COCO PDF -
AcroFOD: An Adaptive Method for Cross-Domain Few-Shot Object Detection ECCV 2022 Cityscapes & SIM10k PDF CODE
Kernelized Few-shot Object Detection with Efficient Integral Aggregation CVPR 2022 PASCAL VOC & MS COCO PDF CODE
Label, Verify, Correct: A Simple Few Shot Object Detection Method CVPR 2022 PASCAL VOC & MS COCO PDF CODE
Few-Shot Object Detection with Fully Cross-Transformer CVPR 2022 PASCAL VOC & MS COCO PDF -
Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment AAAI 2022 PASCAL VOC & MS COCO PDF CODE
Few-Shot Object Detection by Attending to Per-Sample-Prototype WACV 2022 PASCAL VOC & MS COCO PDF -

2021

Title Venue Dataset PDF CODE
Generalized and Discriminative Few-Shot Object Detection via SVD-Dictionary Enhancement NeurIPS 2021 PASCAL VOC & MS COCO PDF CODE
Few-Shot Object Detection via Association and DIscrimination NeurIPS 2021 PASCAL VOC & MS COCO PDF CODE
Adaptive Image Transformer for One-Shot Object Detection CVPR 2021 PASCAL VOC & MS COCO PDF CODE
Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection CVPR 2021 PASCAL VOC & MS COCO PDF CODE
Generalized Few-Shot Object Detection without Forgetting CVPR 2021 PASCAL VOC & MS COCO PDF CODE
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection CVPR 2021 PASCAL VOC & MS COCO PDF CODE
Few-Shot Object Detection via Classification Refinement and Distractor Retreatment CVPR 2021 PASCAL VOC & MS COCO PDF -
Transformation Invariant Few-Shot Object Detection CVPR 2021 PASCAL VOC & MS COCO PDF -
UniT: Unified Knowledge Transfer for Any-shot Object Detection and Segmentation CVPR 2021 PASCAL VOC & MS COCO PDF CODE
FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter CVPR 2021 MS COCO PDF CODE
Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection CVPR 2021 PASCAL VOC & MS COCO PDF -
FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding CVPR 2021 PASCAL VOC & MS COCO PDF CODE
Accurate Few-shot Object Detection with Support-Query Mutual Guidance and Hybrid Loss CVPR 2021 PASCAL VOC & MS COCO PDF -
Hallucination Improves Few-Shot Object Detection CVPR 2021 PASCAL VOC & MS COCO PDF CODE
Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks ICCV 2021 PASCAL VOC & MS COCO PDF CODE
Universal-Prototype Enhancing for Few-Shot Object Detection ICCV 2021 PASCAL VOC & MS COCO PDF CODE
DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection ICCV 2021 PASCAL VOC & MS COCO PDF CODE
Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning ArXiv 2021 PASCAL VOC & MS COCO PDF CODE

2020

Title Venue Dataset PDF CODE
Restoring Negative Information in Few-Shot Object Detection NeurIPS 2020 PASCAL VOC & ImageNet-LOC PDF CODE
Context-Transformer: Tackling Object Confusion for Few-Shot Detection AAAI 2020 PASCAL VOC & MS COCO PDF CODE
Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector CVPR 2020 MS COCO & ImageNet-LOC PDF CODE
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild ECCV 2020 PASCAL VOC & MS COCO PDF CODE
Multi-Scale Positive Sample Refinement for Few-Shot Object Detection ECCV 2020 PASCAL VOC & MS COCO PDF CODE
META-RCNN: META LEARNING FOR FEW-SHOT OBJECT DETECTION ICLR 2020 PASCAL VOC & ImageNet-LOC PDF -
Frustratingly Simple Few-Shot Object Detection ICML 2020 PASCAL VOC & MS COCO & LVIS PDF CODE

2019

Title Venue Dataset PDF CODE
Few-shot Object Detection via Feature Reweighting ICCV 2019 PASCAL VOC & MS COCO PDF CODE
RepMet: Representative-based metric learning for classification and few-shot object detection CVPR 2019 PASCAL VOC & ImageNet-LOC PDF CODE
Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning ICCV 2019 PASCAL VOC & MS COCO PDF CODE
MetaDet: Meta-Learning to Detect Rare Objects ICCV 2019 PASCAL VOC & MS COCO PDF -
One-Shot Object Detection with Co-Attention and Co-Excitation NeurIPS 2019 PASCAL VOC & MS COCO PDF CODE

2018

Title Venue Dataset PDF CODE
Few-example object detection with model communication TPAMI 2018 PASCAL VOC & MS COCO & ILSVRC PDF -
LSTD: A Low-Shot Transfer Detector for Object Detection AAAI 2018 PASCAL VOC & MS COCO & ImageNet2015 PDF -

Datasets

Most few-shot object detection papers usually follow the experimental setup in 《Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning》 and 《Few-shot Object Detection via Feature Reweighting》 and conduct experiments on PASCAL VOC and MS COCO datasets.

PASCAL VOC

For Pascal VOC, the model is trained on the trainval sets of VOC 2007 and 2012, and tested on VOC 2007 test set. The dataset is partitioned into three base/novel splits, where 5 categories are selected as novel classes and others are base classes. The novel classes in each split are as follows:

Split Novel Class
1 bird, bus, cow, mbike, sofa
2 aero, bottle, cow, horse, sofa
3 boat, cat, mbike, sheep, sofa

MS COCO

MS COCO with 80 object categories including the 20 categories in PASCAL VOC. The 20 classes included in PASCAL VOC are set as novel classes, then the rest 60 classes in COCO are as base classes. The union of 80k train images and a 35k subset of validation images (trainval35k) are used for training, and the evaluation is based on the remaining 5k val images (minival).

Acknowledgements

Thanks to Yongqiang Mao for the ideas and templates.