MDETR - Modulated Detection for End-to-End Multi-Modal Understanding

Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed vocabulary of objects and attributes. This makes it challenging for such systems to capture the long tail of visual concepts expressed in free form text. In this paper we propose MDETR, an end-to-end modulated detector that detects objects in an image conditioned on a raw text query, like a caption or a question. We use a transformer-based architecture to reason jointly over text and image by fusing the two modalities at an early stage of the model. We pre-train the network on 1.3M text-image pairs, mined from pre-existing multi-modal datasets having explicit alignment between phrases in text and objects in the image. We then fine-tune on several downstream tasks such as phrase grounding, referring expression comprehension and segmentation, achieving state-of-the-art results on popular benchmarks. We also investigate the utility of our model as an object detector on a given label set when fine-tuned in a few-shot setting. We show that our pre-training approach provides a way to handle the long tail of object categories which have very few labelled instances. Our approach can be easily extended for visual question answering, achieving competitive performance on GQA and CLEVR. The code and models are available at this https URL.

Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed vocabulary of objects and attributes. This makes it challenging for such systems to capture the long tail of visual concepts expressed in free form text. In this paper we propose MDETR, an end-to-end modulated detector that detects objects in an image conditioned on a raw text query, like a caption or a question. We use a transformer-based architecture to reas

saved by

• Kalie C

related reading

• Multi-View Transformer for 3D Visual Groundingarxiv.org
• [2301.13823] Grounding Language Models to Images for Multimodal Generationarxiv.org
• PLA: Language-Driven Open-Vocabulary 3D Scene Understandingarxiv.org
• ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenesecva.net
• Unified Multimodal Models as Auto-Encodersarxiv.org
• TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answeringarxiv.org
• [2304.06718] Segment Everything Everywhere All at Oncearxiv.org
• Feature-wise transformationsdistill.pub
• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• Enhancing 3D Object Detection with 2D Detection-Guided Query Anchorsarxiv.org
• Amodal Detection of 3D Objects: Inferring 3D Bounding Boxes from 2D Ones in RGB-Depth Imagescis.temple.edu
• 2403.09611.pdfarxiv.org