Related papers: Visual Exemplar Driven Task-Prompting for Unified …
Performing multiple heterogeneous visual tasks in dynamic scenes is a hallmark of human perception capability. Despite remarkable progress in image and video recognition via representation learning, current research still focuses on…
Autonomous driving systems require a comprehensive understanding of the environment, achieved by extracting visual features essential for perception, planning, and control. However, models trained solely on single-task objectives or generic…
Visual Prompting is a technique for teaching models to perform a visual task via in-context examples, without any additional training. In this work, we analyze the activations of MAE-VQGAN, a recent Visual Prompting model, and find task…
Bird's-Eye-View (BEV) perception has become a vital component of autonomous driving systems due to its ability to integrate multiple sensor inputs into a unified representation, enhancing performance in various downstream tasks. However,…
Visual prompting (VP) is an emerging parameter-efficient fine-tuning approach to adapting pre-trained vision models to solve various downstream image-classification tasks. However, there has hitherto been little systematic study of the…
Traffic scene recognition, which requires various visual classification tasks, is a critical ingredient in autonomous vehicles. However, most existing approaches treat each relevant task independently from one another, never considering the…
In this paper, we present BEVerse, a unified framework for 3D perception and prediction based on multi-camera systems. Unlike existing studies focusing on the improvement of single-task approaches, BEVerse features in producing…
In daily life, graphic symbols, such as traffic signs and brand logos, are ubiquitously utilized around us due to its intuitive expression beyond language boundary. We tackle an open-set graphic symbol recognition problem by one-shot…
Aiming towards a holistic understanding of multiple downstream tasks simultaneously, there is a need for extracting features with better transferability. Though many latest self-supervised pre-training methods have achieved impressive…
Autonomous vehicle perception typically relies on modular pipelines that decompose the task into detection, tracking, and prediction. While interpretable, these pipelines suffer from error accumulation and limited inter-task synergy.…
This technical report presents our solution for the RoboSense Challenge at IROS 2025, which evaluates Vision-Language Models (VLMs) on autonomous driving scene understanding across perception, prediction, planning, and corruption detection…
Concurrent processing of multiple autonomous driving 3D perception tasks within the same spatiotemporal scene poses a significant challenge, in particular due to the computational inefficiencies and feature competition between tasks when…
Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures…
Prompt Tuning, conditioning on task-specific learned prompt vectors, has emerged as a data-efficient and parameter-efficient method for adapting large pretrained vision-language models to multiple downstream tasks. However, existing…
We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation. With predictions for these tasks we gain a more holistic understanding of persons, which…
Multi-task visual perception has a wide range of applications in scene understanding such as autonomous driving. In this work, we devise an efficient unified framework to solve multiple common perception tasks, including instance…
Vision Transformers have shown great performance in single tasks such as classification and segmentation. However, real-world problems are not isolated, which calls for vision transformers that can perform multiple tasks concurrently.…
Task-oriented object detection aims to find objects suitable for accomplishing specific tasks. As a challenging task, it requires simultaneous visual data processing and reasoning under ambiguous semantics. Recent solutions are mainly…
Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining} (VEP), a method that learns generalizable representations…
Large-scale pre-trained models have achieved remarkable success in various computer vision tasks. A standard approach to leverage these models is to fine-tune all model parameters for downstream tasks, which poses challenges in terms of…