中文
相关论文

相关论文: Addressing Out-of-Distribution Challenges in Image…

200 篇论文

Systematics contaminate observables, leading to distribution shifts relative to theoretically simulated signals-posing a major challenge for using pre-trained models to label such observables. Since systematics are often poorly understood…

天体物理仪器与方法 · 物理学 2025-11-18 Sultan Hassan , Sambatra Andrianomena , Benjamin D. Wandelt

Identifying unexpected domain-shifted instances in natural language processing is crucial in real-world applications. Previous works identify the out-of-distribution (OOD) instance by leveraging a single global feature embedding to…

计算与语言 · 计算机科学 2024-03-20 Jinan Zou , Maihao Guo , Yu Tian , Yuhao Lin , Haiyao Cao , Lingqiao Liu , Ehsan Abbasnejad , Javen Qinfeng Shi

Robust out-of-distribution (OOD) detection is an indispensable component of modern artificial intelligence (AI) systems, especially in safety-critical applications where models must identify inputs from unfamiliar classes not seen during…

机器学习 · 计算机科学 2025-09-09 Tarhib Al Azad , Shahana Ibrahim

The rapid development of generative artificial intelligence (AI) has introduced significant opportunities for enhancing the efficiency and accuracy of image transmission within semantic communication systems. Despite these advancements,…

计算机视觉与模式识别 · 计算机科学 2025-09-29 Qiyu Ma , Wanli Ni , Zhijin Qin

Most classification and segmentation datasets assume a closed-world scenario in which predictions are expressed as distribution over a predetermined set of visual classes. However, such assumption implies unavoidable and often unnoticeable…

计算机视觉与模式识别 · 计算机科学 2018-10-02 Petra Bevandić , Ivan Krešo , Marin Oršić , Siniša Šegvić

While progress has been made on the visual question answering leaderboards, models often utilize spurious correlations and priors in datasets under the i.i.d. setting. As such, evaluation on out-of-distribution (OOD) test samples has…

计算机视觉与模式识别 · 计算机科学 2020-10-19 Tejas Gokhale , Pratyay Banerjee , Chitta Baral , Yezhou Yang

We present a new methodology for detecting out-of-distribution (OOD) images by utilizing norms of the score estimates at multiple noise scales. A score is defined to be the gradient of the log density with respect to the input data. Our…

机器学习 · 计算机科学 2021-03-24 Ahsan Mahmood , Junier Oliva , Martin Styner

The paper demonstrate that simple adjustments of the fine-tuning recipes of multimodal large language models (MLLM) are sufficient to mitigate catastrophic forgetting. On visual question answering, we design a 2x2 experimental framework to…

计算机视觉与模式识别 · 计算机科学 2026-03-17 He Li , Yuhui Zhang , Xiaohan Wang , Kaifeng Lyu , Serena Yeung-Levy

A crucial requirement for machine learning algorithms is not only to perform well, but also to show robustness and adaptability when encountering novel scenarios. One way to achieve these characteristics is to endow the deep learning models…

计算机视觉与模式识别 · 计算机科学 2025-02-26 Eduardo Aguilar , Bogdan Raducanu , Petia Radeva

Reliable out-of-distribution (OOD) detection is fundamental to implementing safer modern machine learning (ML) systems. In this paper, we introduce Igeood, an effective method for detecting OOD samples. Igeood applies to any pre-trained…

Semantic-oriented communication has been considered as a promising to boost the bandwidth efficiency by only transmitting the semantics of the data. In this paper, we propose a multi-level semantic aware communication system for wireless…

图像与视频处理 · 电气工程与系统科学 2023-12-11 Zhenguo Zhang , Qianqian Yang , Shibo He , Mingyang Sun , Jiming Chen

Underwater communication is essential for environmental monitoring, marine biology research, and underwater exploration. Traditional underwater communication faces limitations like low bandwidth, high latency, and susceptibility to noise,…

计算机视觉与模式识别 · 计算机科学 2024-08-27 Weilong Chen , Wenxuan Xu , Haoran Chen , Xinran Zhang , Zhijin Qin , Yanru Zhang , Zhu Han

Large Language Model (LLM) has demonstrated significant ability in various Natural Language Processing tasks. However, their effectiveness is highly dependent on the phrasing of the task prompt, leading to research on automatic prompt…

计算与语言 · 计算机科学 2024-02-06 Moxin Li , Wenjie Wang , Fuli Feng , Yixin Cao , Jizhi Zhang , Tat-Seng Chua

This paper proposes a framework combining Neural Ordinary Differential Equations (Neural ODEs) and robust control theory to enhance the interpretability and control of large language models (LLMs). By utilizing Neural ODEs to model the…

机器学习 · 计算机科学 2025-02-25 Yukun Zhang , Qi Dong

Deep learning has led to remarkable strides in scene understanding with panoptic segmentation emerging as a key holistic scene interpretation task. However, the performance of panoptic segmentation is severely impacted in the presence of…

计算机视觉与模式识别 · 计算机科学 2023-10-19 Rohit Mohan , Kiran Kumaraswamy , Juana Valeria Hurtado , Kürsat Petek , Abhinav Valada

Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes. When deployed in an open world, the reliability of these models depends on their ability not only to classify in-distribution pixels but…

计算机视觉与模式识别 · 计算机科学 2023-08-22 Yuyuan Liu , Choubo Ding , Yu Tian , Guansong Pang , Vasileios Belagiannis , Ian Reid , Gustavo Carneiro

Out-of-distribution (OOD) detection aims to identify test examples that do not belong to the training distribution and are thus unlikely to be predicted reliably. Despite a plethora of existing works, most of them focused only on the…

机器学习 · 计算机科学 2023-11-07 Reza Averly , Wei-Lun Chao

Out-of-distribution (OOD) detection remains challenging for deep learning models, particularly when test-time OOD samples differ significantly from training outliers. We propose OODD, a novel test-time OOD detection method that dynamically…

计算机视觉与模式识别 · 计算机科学 2025-03-14 Yifeng Yang , Lin Zhu , Zewen Sun , Hengyu Liu , Qinying Gu , Nanyang Ye

Out-of-distribution (OOD) detection is essential for model trustworthiness which aims to sensitively identify semantic OOD samples and robustly generalize for covariate-shifted OOD samples. However, we discover that the superior OOD…

机器学习 · 计算机科学 2024-10-16 Qingyang Zhang , Qiuxuan Feng , Joey Tianyi Zhou , Yatao Bian , Qinghua Hu , Changqing Zhang

Multi-modal Large Language Models (MLLMs) are capable of precisely extracting high-level semantic information from multi-modal data, enabling multi-task understanding and generation. This capability facilitates more efficient and…

信息论 · 计算机科学 2025-02-25 Feibo Jiang , Siwei Tu , Li Dong , Kezhi Wang , Kun Yang , Cunhua Pan
‹ 上一页 1 8 9 10 下一页 ›