Related papers: TSLA: A Task-Specific Learning Adaptation for Sema…

A key challenge for autonomous driving lies in maintaining real-time situational awareness regarding surrounding obstacles under strict latency constraints. The high processing requirements coupled with limited onboard computational…

We present a novel approach for unsupervised road segmentation in adverse weather conditions such as rain or fog. This includes a new algorithm for source-free domain adaptation (SFDA) using self-supervised learning. Moreover, our approach…

While most approaches to semantic reasoning have focused on improving performance, in this paper we argue that computational times are very important in order to enable real time applications such as autonomous driving. Towards this goal,…

Fine-tuning large language models (LLMs) is computationally expensive, and Low-Rank Adaptation (LoRA) provides a cost-effective solution by approximating weight updates through low-rank matrices. In real-world scenarios, LLMs are fine-tuned…

Specialized Deep Learning (DL) acceleration stacks, designed for a specific set of frameworks, model architectures, operators, and data types, offer the allure of high performance while sacrificing flexibility. Changes in algorithms,…

Accurate, computationally efficient, and adaptive vehicle models are essential for autonomous vehicle control. Hybrid models that combine a nominal model with a Gaussian Process (GP)-based residual model have emerged as a promising…

Domain shift is a major problem for deploying deep networks in clinical practice. Network performance drops significantly with (target) images obtained differently than its (source) training data. Due to a lack of target label data, most…

Domain adaptation aims to exploit the knowledge in source domain to promote the learning tasks in target domain, which plays a critical role in real-world applications. Recently, lots of deep learning approaches based on autoencoders have…

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training…

Multi-task learning (MTL) is a subfield of machine learning with important applications, but the multi-objective nature of optimization in MTL leads to difficulties in balancing training between tasks. The best MTL optimization methods…

Foundation segmentation models such as the Segment Anything Model (SAM) exhibit strong zero-shot generalization through large-scale pretraining, but adapting them to domain-specific semantic segmentation remains challenging, particularly…

The perception system for autonomous driving generally requires to handle multiple diverse sub-tasks. However, current algorithms typically tackle individual sub-tasks separately, which leads to low efficiency when aiming at obtaining…

In this paper, we present a direct adaptation strategy (ADAS), which aims to directly adapt a single model to multiple target domains in a semantic segmentation task without pretrained domain-specific models. To do so, we design a…

In recent years, the concept of artificial intelligence (AI) has become a prominent keyword because it is promising in solving complex tasks. The need for human expertise in specific areas may no longer be needed because machines have…

Although unsupervised domain adaptation methods have achieved remarkable performance in semantic scene segmentation in visual perception for self-driving cars, these approaches remain impractical in real-world use cases. In practice, the…

Recently, foundation models trained on massive datasets to adapt to a wide range of tasks have attracted considerable attention and are actively being explored within the computer vision community. Among these, the Segment Anything Model…

Cross-Domain Few-Shot Learning~(CDFSL) methods typically parameterize models with task-agnostic and task-specific parameters. To adapt task-specific parameters, recent approaches have utilized fixed optimization strategies, despite their…

When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks…

Hardware accelerators, such as those based on GPUs and FPGAs, offer an excellent opportunity to efficiently parallelize functionalities. Recently, modern embedded platforms started being equipped with such accelerators, resulting in a…

Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles. To acquire a complete $180^\circ$ semantic understanding of the forward surroundings, we…