# Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection

arXiv: https://arxiv.org/abs/2412.17800 · HTML: https://mlsanity.com/paper/2412.17800/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [Seesaw Loss for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2008.10032/) (2020)
- [CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching](https://mlsanity.com/paper/2303.13076/) (2023)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Cross-domain Detection via Graph-induced Prototype Alignment](https://mlsanity.com/paper/2003.12849/) (2020)
- [V3Det: Vast Vocabulary Visual Detection Dataset](https://mlsanity.com/paper/2304.03752/) (2023)
- [Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images](https://mlsanity.com/paper/2205.13764/) (2022)
- [Universal-Prototype Enhancing for Few-Shot Object Detection](https://mlsanity.com/paper/2103.01077/) (2021)
- [Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding](https://mlsanity.com/paper/2206.03484/) (2022)

## Built on by (most cited first, 1 of 1)

- [CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection](https://mlsanity.com/paper/2503.18430/) (2025)

## Abstract (arXiv)

Enabling models to recognize vast open-world categories has been a longstanding pursuit in object detection. By leveraging the generalization capabilities of vision-language models, current open-world detectors can recognize a broader range of vocabularies, despite being trained on limited categories. However, when the scale of the category vocabularies during training expands to a real-world level, previous classifiers aligned with coarse class names significantly reduce the recognition performance of these detectors. In this paper, we introduce Prova, a multi-modal prototype classifier for vast-vocabulary object detection. Prova extracts comprehensive multi-modal prototypes as initialization of alignment classifiers to tackle the vast-vocabulary object recognition failure problem. On V3Det, this simple method greatly enhances the performance among one-stage, two-stage, and DETR-based detectors with only additional projection layers in both supervised and open-vocabulary settings. In particular, Prova improves Faster R-CNN, FCOS, and DINO by 3.3, 6.2, and 2.9 AP respectively in the supervised setting of V3Det. For the open-vocabulary setting, Prova achieves a new state-of-the-art performance with 32.8 base AP and 11.0 novel AP, which is of 2.6 and 4.3 gain over the previous methods.