中文
相关论文

相关论文: Lightweight Facial Landmark Detection in Thermal I…

200 篇论文

In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Ngoc Tuyen Do , Tri Nhu Do

Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely, training and test data do not cover the same set of data…

机器学习 · 计算机科学 2024-08-15 Dino Ienco , Cassio Fraga Dantas

Due to limitations in data quality, some essential visual tasks are difficult to perform independently. Introducing previously unavailable information to transfer informative dark knowledge has been a common way to solve such hard tasks.…

计算机视觉与模式识别 · 计算机科学 2023-06-29 Lingyu Si , Hongwei Dong , Wenwen Qiang , Junzhi Yu , Wenlong Zhai , Changwen Zheng , Fanjiang Xu , Fuchun Sun

Online HD map construction is a fundamental task in autonomous driving systems, aiming to acquire semantic information of map elements around the ego vehicle based on real-time sensor inputs. Recently, several approaches have achieved…

计算机视觉与模式识别 · 计算机科学 2025-08-25 Ziyang Yan , Ruikai Li , Zhiyong Cui , Bohan Li , Han Jiang , Yilong Ren , Aoyong Li , Zhenning Li , Sijia Wen , Haiyang Yu

Knowledge distillation is an effective image anomaly detection and localization scheme. However, a major drawback of this scheme is its tendency to overly generalize, primarily due to the similarities between input and supervisory signals.…

计算机视觉与模式识别 · 计算机科学 2025-12-18 Yuxin Jiang , Yunkang Can , Weiming Shen

Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation,…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Junhong Liu , Yuan Zhang , Tao Huang , Wenchao Xu , Renyu Yang

Feature-based knowledge distillation aims to transfer intermediate representations from a teacher LLM model to a student. Existing approaches typically rely on direct feature matching or learned projections, implicitly treating…

计算与语言 · 计算机科学 2026-02-11 Khouloud Saadi , Di Wang

Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from a high-capacity teacher model to a smaller student model by aligning their output distributions. However, existing methods often underperform in…

计算机视觉与模式识别 · 计算机科学 2026-03-25 Seonghak Kim

Knowledge distillation (KD) is an effective model compression technique that transfers knowledge from a high-performance teacher to a lightweight student, reducing computational and storage costs while maintaining competitive accuracy.…

计算机视觉与模式识别 · 计算机科学 2025-11-17 Fengming Yu , Haiwei Pan , Kejia Zhang , Jian Guan , Haiying Jiang

Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challenges for deployment in resource-constrained scenarios. Knowledge Distillation (KD) offers…

计算机视觉与模式识别 · 计算机科学 2026-04-17 Haoyi Sun , Xiaoxiao Wang , Ning Mao , Qian Wang , Lifu Mu , Wen Zheng , Tao Wei , Wei Chen

Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene…

计算机视觉与模式识别 · 计算机科学 2026-03-18 Junseok Lee , Sungho Shin , Seongju Lee , Kyoobin Lee

Multi-modal RGB and Depth (RGBD) data are predominant in many domains such as robotics, autonomous driving and remote sensing. The combination of these multi-modal data enhances environmental perception by providing 3D spatial context,…

计算机视觉与模式识别 · 计算机科学 2025-06-02 Roger Ferrod , Cássio F. Dantas , Luigi Di Caro , Dino Ienco

The problem of missing modalities is both critical and non-trivial to be handled in multi-modal models. It is common for multi-modal tasks that certain modalities contribute more compared to other modalities, and if those important…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Hu Wang , Congbo Ma , Jianpeng Zhang , Yuan Zhang , Jodie Avery , Louise Hull , Gustavo Carneiro

As a special type of multimedia data, Lithography Hotspot Detection (LHD) training often requires stronger privacy protection than conventional multimedia data, and federated learning provides a promising potential solution to this…

机器学习 · 计算机科学 2026-05-01 Yuqi Li , Xingyou Lin , Yanli Li , Kai Zhang , Chuanguang Yang , Zhongliang Guo , Jianping Gou , Tingwen Huang , Yingli Tian

Radar-camera fusion methods have emerged as a cost-effective approach for 3D object detection but still lag behind LiDAR-based methods in performance. Recent works have focused on employing temporal fusion and Knowledge Distillation (KD)…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Geonho Bang , Minjae Seong , Jisong Kim , Geunju Baek , Daye Oh , Junhyung Kim , Junho Koh , Jun Won Choi

Temperature plays a pivotal role in moderating label softness in the realm of knowledge distillation (KD). Traditional approaches often employ a static temperature throughout the KD process, which fails to address the nuanced complexities…

机器学习 · 计算机科学 2024-04-22 Yukang Wei , Yu Bai

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We demonstrate that…

计算机视觉与模式识别 · 计算机科学 2021-06-07 Fei Ding , Yin Yang , Hongxin Hu , Venkat Krovi , Feng Luo

Recent advancements in camera-based 3D object detection have introduced cross-modal knowledge distillation to bridge the performance gap with LiDAR 3D detectors, leveraging the precise geometric information in LiDAR point clouds. However,…

计算机视觉与模式识别 · 计算机科学 2024-07-16 Sanmin Kim , Youngseok Kim , Sihwan Hwang , Hyeonjun Jeong , Dongsuk Kum

The gap in representations between image and video makes Image-to-Video Re-identification (I2V Re-ID) challenging, and recent works formulate this problem as a knowledge distillation (KD) process. In this paper, we propose a mutual…

计算机视觉与模式识别 · 计算机科学 2022-01-25 Pichao Wang , Fan Wang , Hao Li

Knowledge distillation (KD) is a technique for transferring knowledge from complex teacher models to simpler student models, significantly enhancing model efficiency and accuracy. It has demonstrated substantial advancements in various…

‹ 上一页 1 2 3 10 下一页 ›