中文
相关论文

相关论文: Adaptive Slot Attention: Object Discovery with Dyn…

200 篇论文

For anomaly detection (AD), early approaches often train separate models for individual classes, yielding high performance but posing challenges in scalability and resource management. Recent efforts have shifted toward training a single…

计算机视觉与模式识别 · 计算机科学 2025-07-18 Lei Fan , Junjie Huang , Donglin Di , Anyang Su , Tianyou Song , Maurice Pagnucco , Yang Song

We present a novel framework for compositional video synthesis that leverages temporally consistent object-centric representations, extending our previous work, SlotAdapt, from images to video. While existing object-centric approaches…

计算机视觉与模式识别 · 计算机科学 2025-07-29 Adil Kaan Akan , Yucel Yemez

Most state-of-the-art methods of object detection suffer from poor generalization ability when the training and test data are from different domains, e.g., with different styles. To address this problem, previous methods mainly use holistic…

计算机视觉与模式识别 · 计算机科学 2021-02-16 Aming Wu , Yahong Han , Linchao Zhu , Yi Yang

Online Continual Learning (OCL) is a critical area in machine learning, focusing on enabling models to adapt to evolving data streams in real-time while addressing challenges such as catastrophic forgetting and the stability-plasticity…

Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches…

计算机视觉与模式识别 · 计算机科学 2021-11-04 Yi-Wen Chen , Xiaojie Jin , Xiaohui Shen , Ming-Hsuan Yang

Detection in large-scale scenes is a challenging problem due to small objects and extreme scale variation. It is essential to focus on the image regions of small objects. In this paper, we propose a novel Adaptive Zoom (AdaZoom) network as…

计算机视觉与模式识别 · 计算机科学 2021-06-22 Jingtao Xu , Yali Li , Shengjin Wang

Unsupervised video object segmentation aims to segment the most prominent object in a video sequence. However, the existence of complex backgrounds and multiple foreground objects make this task challenging. To address this issue, we…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Minhyeok Lee , Suhwan Cho , Dogyoon Lee , Chaewon Park , Jungho Lee , Sangyoun Lee

Modern software systems generate extensive heterogeneous log data with dynamic formats, fragmented event sequences, and varying temporal patterns, making anomaly detection both crucial and challenging. To address these complexities, we…

人工智能 · 计算机科学 2025-12-17 Przemek Pospieszny , Wojciech Mormul , Karolina Szyndler , Sanjeev Kumar

We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…

计算机视觉与模式识别 · 计算机科学 2018-08-08 Paul Hongsuck Seo , Zhe Lin , Scott Cohen , Xiaohui Shen , Bohyung Han

Much recent work has been devoted to the problem of ensuring that a neural network's confidence scores match the true probability of being correct, i.e. the calibration problem. Of note, it was found that training with focal loss leads to…

机器学习 · 计算机科学 2023-06-21 Arindam Ghosh , Thomas Schaaf , Matthew R. Gormley

Visual attention, derived from cognitive neuroscience, facilitates human perception on the most pertinent subset of the sensory data. Recently, significant efforts have been made to exploit attention schemes to advance computer vision…

计算机视觉与模式识别 · 计算机科学 2018-10-16 Shi Pu , Yibing Song , Chao Ma , Honggang Zhang , Ming-Hsuan Yang

Recent advances in object-centric representation learning have shown that slot attention-based methods can effectively decompose visual scenes into object slot representations without supervision. However, existing approaches typically…

计算机视觉与模式识别 · 计算机科学 2025-12-11 Huankun Sheng , Ming Li , Yixiang Wei , Yeying Fan , Yu-Hui Wen , Tieliang Gong , Yong-Jin Liu

Category-level 6D object pose estimation aims to estimate the rotation, translation and size of unseen instances within specific categories. In this area, dense correspondence-based methods have achieved leading performance. However, they…

计算机视觉与模式识别 · 计算机科学 2024-03-29 Xiao Lin , Wenfei Yang , Yuan Gao , Tianzhu Zhang

Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already…

计算机视觉与模式识别 · 计算机科学 2022-04-22 Fabio Cermelli , Antonino Geraci , Dario Fontanel , Barbara Caputo

Active learning aims to improve the performance of task model by selecting the most informative samples with a limited budget. Unlike most recent works that focused on applying active learning for image classification, we propose an…

计算机视觉与模式识别 · 计算机科学 2022-04-12 Weiping Yu , Sijie Zhu , Taojiannan Yang , Chen Chen

Compositional Zero-Shot Learning (CZSL) aims to predict unknown compositions made up of attribute and object pairs. Predicting compositions unseen during training is a challenging task. We are exploring Open World Compositional Zero-Shot…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Ans Munir , Faisal Z. Qureshi , Muhammad Haris Khan , Mohsen Ali

We present the first evidence that adaptive learning techniques can boost the discovery of unusual objects within astronomical light curve data sets. Our method follows an active learning strategy where the learning algorithm chooses…

Modular object-centric representations are essential for *human-like reasoning* but are challenging to obtain under spatial ambiguities, *e.g. due to occlusions and view ambiguities*. However, addressing challenges presents both theoretical…

机器学习 · 计算机科学 2025-06-10 Avinash Kori , Francesca Toni , Ben Glocker

Similar to humans perceiving visual scenes as objects, Object-Centric Learning (OCL) can abstract dense images or videos into sparse object-level features. Transformer-based OCL handles complex textures well due to the decoding guidance of…

计算机视觉与模式识别 · 计算机科学 2024-12-23 Rongzhen Zhao , Vivienne Wang , Juho Kannala , Joni Pajarinen

Anomaly detection algorithms are typically applied to static, unchanging, data features hand-crafted by the user. But how does a user systematically craft good features for anomalies that have never been seen? Here we couple deep learning…

机器学习 · 计算机科学 2025-02-04 Alireza Vafaei Sadr , Bruce A. Bassett , Emmanuel Sekyi
‹ 上一页 1 8 9 10 下一页 ›