中文
相关论文

相关论文: Smoothing Slot Attention Iterations and Recurrence…

200 篇论文

Unlike popular solutions based on dense feature maps, Object-Centric Learning (OCL) represents visual scenes as sub-symbolic object-level feature vectors, termed slots, which are highly versatile for tasks involving visual modalities. OCL…

计算机视觉与模式识别 · 计算机科学 2025-11-11 Rongzhen Zhao , Yi Zhao , Juho Kannala , Joni Pajarinen

Object-centric learning (OCL) aspires general and compositional understanding of scenes by representing a scene as a collection of object-centric representations. OCL has also been extended to multi-view image and video datasets to apply…

计算机视觉与模式识别 · 计算机科学 2023-04-03 Jinwoo Kim , Janghyuk Choi , Ho-Jin Choi , Seon Joo Kim

Unsupervised video Object-Centric Learning (OCL) is promising as it enables object-level scene representation and understanding as we humans do. Mainstream video OCL methods adopt a recurrent architecture: An aggregator aggregates current…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Rongzhen Zhao , Jian Li , Juho Kannala , Joni Pajarinen

Learning object-level, structured representations is widely regarded as a key to better generalization in vision and underpins the design of next-generation Pre-trained Vision Models (PVMs). Mainstream Object-Centric Learning (OCL) methods…

计算机视觉与模式识别 · 计算机科学 2025-10-09 Hongjia Liu , Rongzhen Zhao , Haohan Chen , Joni Pajarinen

Object-centric slot attention is a powerful framework for unsupervised learning of structured and explainable representations that can support reasoning about objects and actions, including in surgical videos. While conventional…

图像与视频处理 · 电气工程与系统科学 2026-03-04 Guiqiu Liao , Matjaz Jogan , Marcel Hussing , Kenta Nakahashi , Kazuhiro Yasufuku , Amin Madani , Eric Eaton , Daniel A. Hashimoto

A key human ability is to decompose a scene into distinct objects and use their relationships to understand the environment. Object-centric learning aims to mimic this process in an unsupervised manner. Recently, the slot attention-based…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Pinzhuo Tian , Shengjie Yang , Hang Yu , Alex C. Kot

The extraction of modular object-centric representations for downstream tasks is an emerging area of research. Learning grounded representations of objects that are guaranteed to be stable and invariant promises robust performance across…

机器学习 · 计算机科学 2024-01-26 Avinash Kori , Francesco Locatello , Fabio De Sousa Ribeiro , Francesca Toni , Ben Glocker

Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress…

计算机视觉与模式识别 · 计算机科学 2023-07-24 Ondrej Biza , Sjoerd van Steenkiste , Mehdi S. M. Sajjadi , Gamaleldin F. Elsayed , Aravindh Mahendran , Thomas Kipf

The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning. In the recent culmination of unsupervised object-centric learning, the Slot-Attention module has…

计算机视觉与模式识别 · 计算机科学 2023-02-13 Baoxiong Jia , Yu Liu , Siyuan Huang

A central goal in AI is to represent scenes as compositions of discrete objects, enabling fine-grained, controllable image and video generation. Yet leading diffusion models treat images holistically and rely on text conditioning, creating…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Adil Kaan Akan

Synthetic aperture radar (SAR) images contain not only targets of interest but also complex background clutter, including terrain reflections and speckle noise. In many cases, such clutter exhibits intensity and patterns that resemble…

计算机视觉与模式识别 · 计算机科学 2025-09-12 Oh-Tae Jang , Min-Gon Cho , Kyung-Tae Kim

Unsupervised object-centric learning (OCL) decomposes visual scenes into distinct entities. Slot attention is a popular approach that represents individual objects as latent vectors, called slots. Current methods obtain these slot…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Sebastian Bock , Leonie Schüßler , Krishnakant Singh , Simone Schaub-Meyer , Stefan Roth

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not…

Video Object-Centric Learning seeks to decompose raw videos into a small set of object slots, but existing slot-attention models often suffer from severe over-fragmentation. This is because the model is implicitly encouraged to occupy all…

计算机视觉与模式识别 · 计算机科学 2026-03-25 WonJun Moon , Hyun Seok Seong , Jae-Pil Heo

Self-supervised video Object-Centric Learning (OCL) aims to discover distinct objects and associate them across time, whereas self-supervised Multi-Object Tracking (MOT) focuses on associating pre-defined object detections or segmentations.…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Rongzhen Zhao , Zhiyuan Li , Ruonan Wei , Juho Kannala , Joni Pajarinen

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

Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning. Recently, it was shown that…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Cristian Meo , Akihiro Nakano , Mircea Lică , Aniket Didolkar , Masahiro Suzuki , Anirudh Goyal , Mengmi Zhang , Justin Dauwels , Yutaka Matsuo , Yoshua Bengio

Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level perceptual features. A widely adopted method within OCL is slot…

计算机视觉与模式识别 · 计算机科学 2024-06-14 Ke Fan , Zechen Bai , Tianjun Xiao , Tong He , Max Horn , Yanwei Fu , Francesco Locatello , Zheng Zhang

Object-centric architectures usually apply a differentiable module to the entire feature map to decompose it into sets of entity representations called slots. Some of these methods structurally resemble clustering algorithms, where the…

机器学习 · 计算机科学 2024-12-30 Daniil Kirilenko , Vitaliy Vorobyov , Alexey K. Kovalev , Aleksandr I. Panov

Humans excel at abstracting data and constructing \emph{reusable} concepts, a capability lacking in current continual learning systems. The field of object-centric learning addresses this by developing abstract representations, or slots,…

计算机视觉与模式识别 · 计算机科学 2024-10-02 Vihang Patil , Andreas Radler , Daniel Klotz , Sepp Hochreiter
‹ 上一页 1 2 3 10 下一页 ›