Bor-Shiun Wang,Chien-Yi Wang,Wei-Chen Chiu
Bor-Shiun Wang
Post-hoc and inherently interpretable methods have shown great success in uncovering the inner workings of black-box models, whether by examining them after training or by explicitly designing for interpretability. While these approaches ef...
Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks, Challenges and Baselines [0.03%]
Zekai Zhang,Jinglin Zhang,Qinghui Chen et al.
Zekai Zhang et al.
Large-scale Visual-Language Models (LVLMs) have achieved remarkable success in natural visual tasks, yet their application to industrial defect detection remains challenging due to two fundamental limitations: (i) the scarcity of large-scal...
Jun Shu,Xiang Yuan,Deyu Meng et al.
Jun Shu et al.
Meta learning recently has been heavily researched and helped advance the contemporary machine learning. However, achieving well-performing meta-learning model requires a large amount of training tasks with high-quality meta-data representi...
Yinan Huang,Siqi Miao,Pan Li
Yinan Huang
Message Passing Neural Networks are known to struggle with limited expressivity and capturing long-range dependencies. While Graph Transformers alleviate these issues with global attention modules, their quadratic complexity limits efficien...
Xiaowan Hu,Henan Liu,Ce Zheng et al.
Xiaowan Hu et al.
Video denoising is fundamental to low-level vision and real-world imaging, yet existing self-supervised methods remain fragile under severe noise and complex motion. Most approaches still rely on spatially and temporally discrete grid-based...
Chaoqing Tang,Huanze Zhuang,Guiyun Tian et al.
Chaoqing Tang et al.
Despite large models drive unprecedented growth in data and model parameters, many real-world problems prioritize interpretability and generality, and lack sufficient training data. For instance, in Compressed Sensing (CS) where sparse reco...
Chang Yu,Yisi Luo,Kai Ye et al.
Chang Yu et al.
Implicit neural representation (INR) has emerged as a powerful paradigm for visual data representation. However, classical INR methods represent data in the original space mixed with different frequency components, and several feature encod...
Seeking Flat Minima Over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation [0.03%]
Meixi Zheng,Kehan Wu,Yanbo Fan et al.
Meixi Zheng et al.
The transfer-based black-box adversarial attack setting poses the challenge of crafting an adversarial example (AE) on known surrogate models that remains effective against unseen target models. Due to the practical importance of this task,...
Yang Chen,Haisong Liu,Limin Wang
Yang Chen
Camera-based 3D object detection in BEV (Bird's Eye View) space has drawn great attention over the past few years. Dense detectors typically follow a two-stage pipeline by first constructing a dense BEV feature and then performing object de...
Muhammad Kashif Ali,Eun Woo Im,Dongjin Kim et al.
Muhammad Kashif Ali et al.
Video stabilization remains a fundamental problem in computer vision, particularly pixel-level synthesis solutions for video stabilization, which synthesize full-frame outputs, add to the complexity of this task. These methods aim to enhanc...