Related papers: Visual Perception Engine: Fast and Flexible Multi-…

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…

We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures…

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,…

Low-level vision involves a wide spectrum of tasks, including image restoration, enhancement, stylization, and feature extraction, which differ significantly in both task formulation and output domains. To address the challenge of unified…

Intelligent surveillance systems often handle perceptual tasks such as object detection, facial recognition, and emotion analysis independently, but they lack a unified, adaptive runtime scheduler that dynamically allocates computational…

Collective Perception has attracted significant attention in recent years due to its advantage for mitigating occlusion and expanding the field-of-view, thereby enhancing reliability, efficiency, and, most crucially, decision-making safety.…

While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two primary…

Purpose: Visual perception enables robots to perceive the environment. Visual data is processed using computer vision algorithms that are usually time-expensive and require powerful devices to process the visual data in real-time, which is…

Perception is essential for autonomous driving system. Recent approaches based on Bird's-eye-view (BEV) and deep learning have made significant progress. However, there exists challenging issues including lengthy development cycles, poor…

In robotics, Vision-Language-Action (VLA) models that integrate diverse multimodal signals from multi-view inputs have emerged as an effective approach. However, most prior work adopts static fusion that processes all visual inputs…

Recent advances in diffusion models have achieved remarkable success in isolated computer vision tasks such as text-to-image generation, depth estimation, and optical flow. However, these models are often restricted by a…

Recently, perception task based on Bird's-Eye View (BEV) representation has drawn more and more attention, and BEV representation is promising as the foundation for next-generation Autonomous Vehicle (AV) perception. However, most existing…

Answering visual queries is a complex task that requires both visual processing and reasoning. End-to-end models, the dominant approach for this task, do not explicitly differentiate between the two, limiting interpretability and…

Recognition and reasoning are two pillars of visual understanding. However, these tasks have an imbalance in focus; whereas recent advances in neural networks have shown strong empirical performance in visual recognition, there has been…

The accuracy-speed-memory trade-off is always the priority to consider for several computer vision perception tasks. Previous methods mainly focus on a single or small couple of these tasks, such as creating effective data augmentation,…

Faster inference of deep learning models is highly demanded on edge devices and even servers, for both financial and environmental reasons. To address this issue, we propose SoftNeuro, a novel, high-performance inference framework with…

The superior performance of modern deep networks usually comes with a costly training procedure. This paper presents a new curriculum learning approach for the efficient training of visual backbones (e.g., vision Transformers). Our work is…

With the improvements in the object detection networks, several variations of object detection networks have been achieved impressive performance. However, the performance evaluation of most models has focused on detection accuracy, and…

Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its…

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…