# Revisiting Few-Shot Object Detection with Vision-Language Models

arXiv: https://arxiv.org/abs/2312.14494 · HTML: https://mlsanity.com/paper/2312.14494/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 68 of its 83 references that are in the map.
- First posted on arXiv 22 Dec 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)

## Builds on (most cited first, 30 of 68)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)

## Built on by (most cited first, 30 of 32)

- [Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models](https://mlsanity.com/paper/2505.20612/) (2025)
- [Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning](https://mlsanity.com/paper/2406.11148/) (2024)
- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [RefAV: Towards Planning-Centric Scenario Mining](https://mlsanity.com/paper/2505.20981/) (2025)
- [First Frame Is the Place to Go for Video Content Customization](https://mlsanity.com/paper/2511.15700/) (2025)
- [Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation](https://mlsanity.com/paper/2504.09480/) (2025)
- [Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection](https://mlsanity.com/paper/2406.10115/) (2024)
- [Solving Instance Detection from an Open-World Perspective](https://mlsanity.com/paper/2503.00359/) (2025)
- [InfoDet: A Dataset for Infographic Element Detection](https://mlsanity.com/paper/2505.17473/) (2025)
- [Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset](https://mlsanity.com/paper/2603.23607/) (2026)
- [Beyond Few-shot Object Detection: A Detailed Survey](https://mlsanity.com/paper/2408.14249/) (2024)
- [HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning](https://mlsanity.com/paper/2504.15323/) (2025)
- [Enabling Validation for Robust Few-Shot Recognition](https://mlsanity.com/paper/2506.04713/) (2025)
- [Class-Aware Prototype Learning with Negative Contrast for Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2510.19802/) (2025)
- [nuScenes Revisited: Progress and Challenges in Autonomous Driving](https://mlsanity.com/paper/2512.02448/) (2025)
- [Multi-label Instance-level Generalised Visual Grounding in Agriculture](https://mlsanity.com/paper/2603.06699/) (2026)
- [DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection](https://mlsanity.com/paper/2603.23455/) (2026)
- [A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps](https://mlsanity.com/paper/2603.28182/) (2026)
- [Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability](https://mlsanity.com/paper/2410.15315/) (2024)
- [On-the-Fly OVD Adaptation with FLAME: Few-shot Localization via Active Marginal-Samples Exploration](https://mlsanity.com/paper/2510.17670/) (2025)
- [Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRA](https://mlsanity.com/paper/2512.10521/) (2025)
- [Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness](https://mlsanity.com/paper/2602.19615/) (2026)
- [D3VL: Understanding Driving Scenes from 3D Time Series Data and Video with Language Models](https://mlsanity.com/paper/2607.19528/) (2026)
- [AutoExpert: Automating 3D LiDAR Annotation from Expert-Crafted Guidelines](https://mlsanity.com/paper/2506.02914/) (2025)
- [ZERO: Industry-ready Vision Foundation Model with Multi-modal Prompts](https://mlsanity.com/paper/2507.04270/) (2025)
- [In-Context Adaptation of VLMs for Few-Shot Cell Detection in Optical Microscopy](https://mlsanity.com/paper/2511.05565/) (2025)
- [UniFlow: Zero-Shot LiDAR Scene Flow for Autonomous Vehicles](https://mlsanity.com/paper/2511.18254/) (2025)
- [Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective](https://mlsanity.com/paper/2512.10244/) (2025)
- [Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors](https://mlsanity.com/paper/2512.15748/) (2025)
- [From Words to Wavelengths: VLMs for Few-Shot Multispectral Object Detection](https://mlsanity.com/paper/2512.15971/) (2025)

## Abstract (arXiv)

The era of vision-language models (VLMs) trained on web-scale datasets challenges conventional formulations of "open-world" perception. In this work, we revisit the task of few-shot object detection (FSOD) in the context of recent foundational VLMs. First, we point out that zero-shot predictions from VLMs such as GroundingDINO significantly outperform state-of-the-art few-shot detectors (48 vs. 33 AP) on COCO. Despite their strong zero-shot performance, such foundation models may still be sub-optimal. For example, trucks on the web may be defined differently from trucks for a target application such as autonomous vehicle perception. We argue that the task of few-shot recognition can be reformulated as aligning foundation models to target concepts using a few examples. Interestingly, such examples can be multi-modal, using both text and visual cues, mimicking instructions that are often given to human annotators when defining a target concept of interest. Concretely, we propose Foundational FSOD, a new benchmark protocol that evaluates detectors pre-trained on any external data and fine-tuned on multi-modal (text and visual) K-shot examples per target class. We repurpose nuImages for Foundational FSOD, benchmark several popular open-source VLMs, and provide an empirical analysis of state-of-the-art methods. Lastly, we discuss our recent CVPR 2024 Foundational FSOD competition and share insights from the community. Notably, the winning team significantly outperforms our baseline by 23.3 mAP! Our code and dataset splits are available at https://github.com/anishmadan23/foundational_fsod