中文
相关论文

相关论文: MetaSlot: Break Through the Fixed Number of Slots …

200 篇论文

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

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…

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

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

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

Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various aims, including out-of-distribution (OOD) generalization,…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Alexander Rubinstein , Ameya Prabhu , Matthias Bethge , Seong Joon Oh

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

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

Developing deep learning models that effectively learn object-centric representations, akin to human cognition, remains a challenging task. Existing approaches facilitate object discovery by representing objects as fixed-size vectors,…

计算机视觉与模式识别 · 计算机科学 2023-12-11 Aniket Didolkar , Anirudh Goyal , Yoshua Bengio

Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Aniket Didolkar , Andrii Zadaianchuk , Rabiul Awal , Maximilian Seitzer , Efstratios Gavves , Aishwarya Agrawal

The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \emph{slots} or \emph{object files} that compete for local…

计算机视觉与模式识别 · 计算机科学 2023-06-06 Ayush Chakravarthy , Trang Nguyen , Anirudh Goyal , Yoshua Bengio , Michael C. Mozer

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

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

Object-centric learning aims to decompose an input image into a set of meaningful object files (slots). These latent object representations enable a variety of downstream tasks. Yet, object-centric learning struggles on real-world datasets,…

计算机视觉与模式识别 · 计算机科学 2025-06-10 Krishnakant Singh , Simone Schaub-Meyer , Stefan Roth

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

Object-Centric Learning (OCL) aggregates image or video feature maps into object-level feature vectors, termed \textit{slots}. It's self-supervision of reconstructing the input from slots struggles with complex object textures, thus Vision…

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

Learning modular object-centric representations is crucial for systematic generalization. Existing methods show promising object-binding capabilities empirically, but theoretical identifiability guarantees remain relatively underdeveloped.…

Object-centric learning (OCL) aims to learn representations of individual objects within visual scenes without manual supervision, facilitating efficient and effective visual reasoning. Traditional OCL methods primarily employ bottom-up…

计算机视觉与模式识别 · 计算机科学 2024-11-11 Dongwon Kim , Seoyeon Kim , Suha Kwak

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

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
‹ 上一页 1 2 3 10 下一页 ›