paper-with-me

홈 › Papers

ContextVLM: Zero-Shot and Few-Shot Context Understanding for Autonomous Driving using Vision Language Models

2024-08-30 · Shounak Sural, Naren, Ragunathan Rajkumar

In recent years, there has been a notable increase in the development of autonomous vehicle (AV) technologies aimed at improving safety in transportation systems. While AVs have been deployed in the real-world to some extent, a full-scale deployment requires AVs to robustly navigate through challenges like heavy rain, snow, low lighting, construction zones and GPS signal loss in tunnels. To be able to handle these specific challenges, an AV must reliably recognize the physical attributes of the environment in which it operates. In this paper, we define context recognition as the task of accurately identifying environmental attributes for an AV to appropriately deal with them. Specifically, we define 24 environmental contexts capturing a variety of weather, lighting, traffic and road conditions that an AV must be aware of. Motivated by the need to recognize environmental contexts, we create a context recognition dataset called DrivingContexts with more than 1.6 million context-query pairs relevant for an AV. Since traditional supervised computer vision approaches do not scale well to a variety of contexts, we propose a framework called ContextVLM that uses vision-language models to detect contexts using zero- and few-shot approaches. ContextVLM is capable of reliably detecting relevant driving contexts with an accuracy of more than 95% on our dataset, while running in real-time on a 4GB Nvidia GeForce GTX 1050 Ti GPU on an AV with a latency of 10.5 ms per query.

📄 PDF Abstract BibTeX arXiv:2409.00301

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingGPUNavigate

Methods 이 논문이 사용한 방법론

GPS Greedy Policy Search (GPS) is a simple algorithm that learns a policy for test-time data augmentation based on the predictive performance on a validation set. GPS starts with…
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning

2024-04-15 · Tidiane Camaret Ndir, André Biedenkapp, Noor Awad

In this work, we address the challenge of zero-shot generalization (ZSG) in Reinforcement Learning (RL), where agents must adapt to entirely novel environments without additional training. We argue that understanding and…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Zero-shot Generalization

Language Models as Zero-shot Visual Semantic Learners

2021-07-26 · Yue Jiao, Jonathon Hare, Adam Prügel-Bennett

Visual Semantic Embedding (VSE) models, which map images into a rich semantic embedding space, have been a milestone in object recognition and zero-shot learning. Current approaches to VSE heavily rely on static word em-…

ObjectObject RecognitionWord EmbeddingsZero-Shot Learning

InFoBERT: Zero-Shot Approach to Natural Language Understanding Using Contextualized Word Embedding

2021-09-01 · RANLP 2021 9 · Pavel Burnyshev, Andrey Bout, Valentin Malykh, Irina Piontkovskaya

Natural language understanding is an important task in modern dialogue systems. It becomes more important with the rapid extension of the dialogue systems’ functionality. In this work, we present an approach to zero-shot…

intent-classificationIntent ClassificationIntent Classification and Slot FillingNatural Language Understanding+3

Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments

2025-10-29 · Manjunath Prasad Holenarasipura Rajiv, B. M. Vidyavathi arxiv

Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled…

Scene UnderstandingActivity DetectionObject Recognition

ResNetVLLM -- Multi-modal Vision LLM for the Video Understanding Task

2025-04-20 · Ahmad Khalil, Mahmoud Khalil, Alioune Ngom

In this paper, we introduce ResNetVLLM (ResNet Vision LLM), a novel cross-modal framework for zero-shot video understanding that integrates a ResNet-based visual encoder with a Large Language Model (LLM. ResNetVLLM addre…

Language ModelingLanguage ModellingLarge Language ModelVideo Understanding