paper-with-me

Papers

Cycle Consistency in Video Object-Centric Learning

2026-05-28 · Rongzhen Zhao, Zhiyuan Li, Ruonan Wei, Juho Kannala, Joni Pajarinen arxiv

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. Although well-established in MOT, Cycle Consistency (CC) cannot naively or explicitly apply to the latent slot space of OCL. Unlike the deterministic and ideal object representations in MOT, OCL slots are inherently stochastic and ambiguous due to non-unique scene decompositions. Enforcing explicit cycle consistency (ECC) on slots imposes rigid mean seeking. This severely penalizes the model for exploring alternative but equally valid decompositions, thereby driving towards feature collapse. To resolve this dilemma, we propose \textit{Implicit Cycle Consistency (ICC)}, which shifts the cycle-consistency constraint from the restrictive slot space to the continuous reconstruction manifold, encouraging slots to reach a soft consensus on collectively interpreting the visual scene rather than forcing rigid point-to-point feature alignment. Extensive experiments on complex video OCL benchmarks demonstrate that ICC avoids feature collapse and outperforms ECC baselines. Our source code, model checkpoints and training logs are provided on https://github.com/Genera1Z/ICC.

📄 PDF Abstract BibTeX arXiv:2605.30211

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Object Tracking

Similar Papers 제목 키워드 기반

Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction

2026-02-22 · Shannan Yan, Leqi Zheng, Keyu Lv, Jingchen Ni 외 arxiv

We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios. We propose a simple…

From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning

2026-02-03 · Hyun Seok Seong, WonJun Moon, Jae-Pil Heo arxiv

Unsupervised object-centric learning models, particularly slot-based architectures, have shown great promise in decomposing complex scenes. However, their reliance on reconstruction-based training creates a fundamental c…

Representation Learning

Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases

2024-10-21 · Cristian Meo, Akihiro Nakano, Mircea Lică, Aniket Didolkar 외

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 …

ObjectQuestion AnsweringVideo PredictionVisual Question Answering

Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video

2026-03-14 · Yuting Tan, Xilong Cheng, Yunxiao Qin, Zhengnan Li 외 arxiv

Humans develop visual intelligence through perceiving and interacting with their environment - a self-supervised learning process grounded in egocentric experience. Inspired by this, we ask how can artificial systems lea…

Self-Supervised LearningSemantic Segmentation

Temporally Consistent Object-Centric Learning by Contrasting Slots

2024-12-18 · CVPR 2025 1 · Anna Manasyan, Maximilian Seitzer, Filip Radovic, Georg Martius 외

Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these repre…

Inductive BiasObjectObject Discovery