# Few-Shot Object Detection via Association and DIscrimination

arXiv: https://arxiv.org/abs/2111.11656 · HTML: https://mlsanity.com/paper/2111.11656/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 56 references that are in the map.
- First posted on arXiv 23 Nov 2021.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Frustratingly Simple Few-Shot Object Detection](https://mlsanity.com/paper/2003.06957/) (2020)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [Low-Shot Learning from Imaginary Data](https://mlsanity.com/paper/1801.05401/) (2018)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild](https://mlsanity.com/paper/2007.12107/) (2020)
- [Multi-Scale Positive Sample Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2007.09384/) (2020)
- [Adaptive Cross-Modal Few-Shot Learning](https://mlsanity.com/paper/1902.07104/) (2019)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [RepMet: Representative-based metric learning for classification and one-shot object detection](https://mlsanity.com/paper/1806.04728/) (2018)
- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection](https://mlsanity.com/paper/2103.01903/) (2021)

## Built on by (most cited first, 30 of 39)

- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [Explore the Power of Synthetic Data on Few-shot Object Detection](https://mlsanity.com/paper/2303.13221/) (2023)
- [Few-Shot Object Detection: A Comprehensive Survey](https://mlsanity.com/paper/2112.11699/) (2021)
- [Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization](https://mlsanity.com/paper/2211.10528/) (2022)
- [Few-Shot Object Detection via Variational Feature Aggregation](https://mlsanity.com/paper/2301.13411/) (2023)
- [Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection](https://mlsanity.com/paper/2304.05096/) (2023)
- [Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection](https://mlsanity.com/paper/2210.05593/) (2022)
- [AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration](https://mlsanity.com/paper/2112.01740/) (2021)
- [Efficient Few-Shot Object Detection via Knowledge Inheritance](https://mlsanity.com/paper/2203.12224/) (2022)
- [Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation](https://mlsanity.com/paper/2301.01156/) (2023)
- [Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection](https://mlsanity.com/paper/2207.11184/) (2022)
- [Learning to Discover and Detect Objects](https://mlsanity.com/paper/2210.10774/) (2022)
- [Logits DeConfusion with CLIP for Few-Shot Learning](https://mlsanity.com/paper/2504.12104/) (2025)
- [Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison](https://mlsanity.com/paper/2203.14205/) (2022)
- [SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection](https://mlsanity.com/paper/2407.02665/) (2024)
- [A Survey of Deep Learning for Low-Shot Object Detection](https://mlsanity.com/paper/2112.02814/) (2021)
- [Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning](https://mlsanity.com/paper/2208.07039/) (2022)
- [Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection](https://mlsanity.com/paper/2504.07060/) (2025)
- [Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection](https://mlsanity.com/paper/2304.12161/) (2023)
- [Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations](https://mlsanity.com/paper/2207.12049/) (2022)
- [An Effective Crop-Paste Pipeline for Few-shot Object Detection](https://mlsanity.com/paper/2302.14452/) (2023)
- [Incremental Few-Shot Learning via Implanting and Compressing](https://mlsanity.com/paper/2203.10297/) (2022)
- [MINI: Mining Implicit Novel Instances for Few-Shot Object Detection](https://mlsanity.com/paper/2205.03381/) (2022)
- [Proposal Distribution Calibration for Few-Shot Object Detection](https://mlsanity.com/paper/2212.07618/) (2022)
- [GPTR: Gestalt-Perception Transformer for Diagram Object Detection](https://mlsanity.com/paper/2212.14232/) (2022)
- [Incremental Few-Shot Object Detection via Simple Fine-Tuning Approach](https://mlsanity.com/paper/2302.09779/) (2023)
- [SepRep-Net: Multi-source Free Domain Adaptation via Model Separation And Reparameterization](https://mlsanity.com/paper/2402.08249/) (2024)
- [UniFS: Universal Few-shot Instance Perception with Point Representations](https://mlsanity.com/paper/2404.19401/) (2024)
- [PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detection](https://mlsanity.com/paper/2408.05674/) (2024)
- [Beyond Few-shot Object Detection: A Detailed Survey](https://mlsanity.com/paper/2408.14249/) (2024)

## Abstract (arXiv)

Object detection has achieved substantial progress in the last decade. However, detecting novel classes with only few samples remains challenging, since deep learning under low data regime usually leads to a degraded feature space. Existing works employ a holistic fine-tuning paradigm to tackle this problem, where the model is first pre-trained on all base classes with abundant samples, and then it is used to carve the novel class feature space. Nonetheless, this paradigm is still imperfect. Durning fine-tuning, a novel class may implicitly leverage the knowledge of multiple base classes to construct its feature space, which induces a scattered feature space, hence violating the inter-class separability. To overcome these obstacles, we propose a two-step fine-tuning framework, Few-shot object detection via Association and DIscrimination (FADI), which builds up a discriminative feature space for each novel class with two integral steps. 1) In the association step, in contrast to implicitly leveraging multiple base classes, we construct a compact novel class feature space via explicitly imitating a specific base class feature space. Specifically, we associate each novel class with a base class according to their semantic similarity. After that, the feature space of a novel class can readily imitate the well-trained feature space of the associated base class. 2) In the discrimination step, to ensure the separability between the novel classes and associated base classes, we disentangle the classification branches for base and novel classes. To further enlarge the inter-class separability between all classes, a set-specialized margin loss is imposed. Extensive experiments on Pascal VOC and MS-COCO datasets demonstrate FADI achieves new SOTA performance, significantly improving the baseline in any shot/split by +18.7. Notably, the advantage is most announced on extremely few-shot scenarios.