English
Related papers

Related papers: Exploring the Reliability of Foundation Model-Base…

200 papers

The prominence of generalized foundation models in vision-language integration has witnessed a surge, given their multifarious applications. Within the natural domain, the procurement of vision-language datasets to construct these…

Computer Vision and Pattern Recognition · Computer Science 2024-09-12 Keumgang Cha , Donggeun Yu , Junghoon Seo

Object detection is integral to a bevy of real-world applications, from robotics to medical image analysis. To be used reliably in such applications, models must be capable of handling unexpected - or novel - objects. The open world object…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Orr Zohar , Alejandro Lozano , Shelly Goel , Serena Yeung , Kuan-Chieh Wang

This paper proposes a novel framework for autonomous drone navigation through a cluttered environment. Control policies are learnt in a low-level environment during training and are applied to a complex environment during inference. The…

Robotics · Computer Science 2021-11-12 Praveen Venkatesh , Viraj Shah , Vrutik Shah , Yash Kamble , Joycee Mekie

This study presents a novel evaluation framework for the Vision-Language Navigation (VLN) task. It aims to diagnose current models for various instruction categories at a finer-grained level. The framework is structured around the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Zehao Wang , Minye Wu , Yixin Cao , Yubo Ma , Meiqi Chen , Tinne Tuytelaars

We present FoundationSLAM, a learning-based monocular dense SLAM system that addresses the absence of geometric consistency in previous flow-based approaches for accurate and robust tracking and mapping. Our core idea is to bridge flow…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Yuchen Wu , Jiahe Li , Fabio Tosi , Matteo Poggi , Jin Zheng , Xiao Bai

Current zero-shot Camouflaged Object Segmentation methods typically employ a two-stage pipeline (discover-then-segment): using MLLMs to obtain visual prompts, followed by SAM segmentation. However, relying solely on MLLMs for camouflaged…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Yilong Yang , Jianxin Tian , Shengchuan Zhang , Liujuan Cao

Surface defect inspection is an important task in industrial inspection. Deep learning-based methods have demonstrated promising performance in this domain. Nevertheless, these methods still suffer from misjudgment when encountering…

Computer Vision and Pattern Recognition · Computer Science 2023-09-25 Xiaoheng Jiang , Shilong Tian , Zhiwen Zhu , Yang Lu , Hao Liu , Li Chen , Shupan Li , Mingliang Xu

Learning diverse skills without hand-crafted reward functions could accelerate reinforcement learning in downstream tasks. However, existing skill discovery methods focus solely on maximizing the diversity of skills without considering…

Artificial Intelligence · Computer Science 2025-10-28 Zhao Yang , Thomas M. Moerland , Mike Preuss , Aske Plaat , Vincent François-Lavet , Edward S. Hu

Source-Free Object Detection (SFOD) has garnered much attention in recent years by eliminating the need of source-domain data in cross-domain tasks, but existing SFOD methods suffer from the Source Bias problem, i.e. the adapted model…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Zhi Cai , Yingjie Gao , Yanan Zhang , Xinzhu Ma , Di Huang

Zeroth-order (ZO) optimization provides a gradient-free alternative to first-order (FO) methods by estimating gradients via finite differences of function evaluations, and has recently emerged as a memory-efficient paradigm for fine-tuning…

Machine Learning · Computer Science 2026-02-24 Yicheng Lang , Changsheng Wang , Yihua Zhang , Mingyi Hong , Zheng Zhang , Wotao Yin , Sijia Liu

Large Language Model (LLM) inference is growing increasingly complex with the rise of Mixture-of-Experts (MoE) models and disaggregated architectures that decouple components like prefill/decode (PD) or attention/FFN (AF) for heterogeneous…

Machine Learning · Computer Science 2025-08-06 Yicheng Feng , Xin Tan , Kin Hang Sew , Yimin Jiang , Yibo Zhu , Hong Xu

Zero-shot object pose estimation enables the retrieval of object poses from images without necessitating object-specific training. In recent approaches this is facilitated by vision foundation models (VFM), which are pre-trained models that…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Bernd Von Gimborn , Philipp Ausserlechner , Markus Vincze , Stefan Thalhammer

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to produce RL algorithms whose policies generalise well to novel unseen situations at deployment time, avoiding overfitting to their training environments.…

Machine Learning · Computer Science 2023-01-20 Robert Kirk , Amy Zhang , Edward Grefenstette , Tim Rocktäschel

Understanding and following natural language instructions while navigating through complex, real-world environments poses a significant challenge for general-purpose robots. These environments often include obstacles and pedestrians, making…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Xiwen Liang , Liang Ma , Shanshan Guo , Jianhua Han , Hang Xu , Shikui Ma , Xiaodan Liang

In open-vocabulary mobile manipulation (OVMM), task success often hinges on the selection of an appropriate base placement for the robot. Existing approaches typically navigate to proximity-based regions without considering affordances,…

Robotics · Computer Science 2026-01-06 Tzu-Jung Lin , Jia-Fong Yeh , Hung-Ting Su , Chung-Yi Lin , Yi-Ting Chen , Winston H. Hsu

This paper introduces an innovative application of foundation models, enabling Unmanned Ground Vehicles (UGVs) equipped with an RGB-D camera to navigate to designated destinations based on human language instructions. Unlike learning-based…

Robotics · Computer Science 2024-10-15 Chanhoe Ryu , Hyunki Seong , Daegyu Lee , Seongwoo Moon , Sungjae Min , D. Hyunchul Shim

Multimodal foundation models offer a promising framework for robotic perception and planning by processing sensory inputs to generate actionable plans. However, addressing uncertainty in both perception (sensory interpretation) and…

Robotics · Computer Science 2025-04-18 Neel P. Bhatt , Yunhao Yang , Rohan Siva , Daniel Milan , Ufuk Topcu , Zhangyang Wang

Zeroth-order optimization is the process of minimizing an objective $f(x)$, given oracle access to evaluations at adaptively chosen inputs $x$. In this paper, we present two simple yet powerful GradientLess Descent (GLD) algorithms that do…

Machine Learning · Computer Science 2020-05-20 Daniel Golovin , John Karro , Greg Kochanski , Chansoo Lee , Xingyou Song , Qiuyi Zhang

Existing methods for multi-agent navigation typically assume fully known environments, offering limited support for partially known scenarios with outdated or imperfect prior maps, such as warehouses or factory floors. There, agents need to…

Large-scale foundation models have become the mainstream deep learning method, while in civil engineering, the scale of AI models is strictly limited. In this work, a vision foundation model is introduced for crack segmentation. Two…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Kang Ge , Chen Wang , Yutao Guo , Yansong Tang , Zhenzhong Hu , Hongbing Chen