# Open-vocabulary Object Detection via Vision and Language Knowledge Distillation

arXiv: https://arxiv.org/abs/2104.13921 · HTML: https://mlsanity.com/paper/2104.13921/

## Key facts

- Cited by 906 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 35 of its 55 references that are in the map.
- First posted on arXiv 28 Apr 2021.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [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)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [Zero-Shot Object Detection](https://mlsanity.com/paper/1804.04340/) (2018)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs](https://mlsanity.com/paper/1803.08035/) (2018)
- [Zero-Shot Learning by Convex Combination of Semantic Embeddings](https://mlsanity.com/paper/1312.5650/) (2013)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Open Vocabulary Scene Parsing](https://mlsanity.com/paper/1703.08769/) (2017)
- [Object Detection with a Unified Label Space from Multiple Datasets](https://mlsanity.com/paper/2008.06614/) (2020)
- [Dont Even Look Once: Synthesizing Features for Zero-Shot Detection](https://mlsanity.com/paper/1911.07933/) (2019)
- [Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts](https://mlsanity.com/paper/1803.06049/) (2018)
- [Link the head to the "beak": Zero Shot Learning from Noisy Text Description at Part Precision](https://mlsanity.com/paper/1709.01148/) (2017)
- [Zero Shot Recognition with Unreliable Attributes](https://mlsanity.com/paper/1409.4327/) (2014)

## Built on by (most cited first, 30 of 906)

- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [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)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Simple Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2205.06230/) (2022)
- [ConceptFusion: Open-set Multimodal 3D Mapping](https://mlsanity.com/paper/2302.07241/) (2023)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [Long-CLIP: Unlocking the Long-Text Capability of CLIP](https://mlsanity.com/paper/2403.15378/) (2024)
- [Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V](https://mlsanity.com/paper/2310.11441/) (2023)

## Abstract (arXiv)

We aim at advancing open-vocabulary object detection, which detects objects described by arbitrary text inputs. The fundamental challenge is the availability of training data. It is costly to further scale up the number of classes contained in existing object detection datasets. To overcome this challenge, we propose ViLD, a training method via Vision and Language knowledge Distillation. Our method distills the knowledge from a pretrained open-vocabulary image classification model (teacher) into a two-stage detector (student). Specifically, we use the teacher model to encode category texts and image regions of object proposals. Then we train a student detector, whose region embeddings of detected boxes are aligned with the text and image embeddings inferred by the teacher. We benchmark on LVIS by holding out all rare categories as novel categories that are not seen during training. ViLD obtains 16.1 mask APr with a ResNet-50 backbone, even outperforming the supervised counterpart by 3.8. When trained with a stronger teacher model ALIGN, ViLD achieves 26.3 APr. The model can directly transfer to other datasets without finetuning, achieving 72.2 AP50 on PASCAL VOC, 36.6 AP on COCO and 11.8 AP on Objects365. On COCO, ViLD outperforms the previous state-of-the-art by 4.8 on novel AP and 11.4 on overall AP. Code and demo are open-sourced at https://github.com/tensorflow/tpu/tree/master/models/official/detection/projects/vild.