Selective Synergistic Learning for Video Object-Centric Learning

Citations

WEB OF SCIENCE

0
Citations

SCOPUS

0

초록

Typical video object-centric learning (VOCL) approaches employ slot-based frameworks that rely on reconstruction-driven encoder–decoder architectures, where learning is mediated by two spatial maps: attention maps from the encoder and object maps from the decoder. As these two distinct maps exhibit different properties, a recent dense alignment strategy attempted to reconcile this discrepancy by enforcing agreement across all spatio-temporal patches via contrastive learning. However, this indiscriminate alignment inadvertently propagates the inherent weaknesses of each module, such as noisy encoder predictions and blurred decoder boundaries. Moreover, computing dense similarities across all pairs incurs a computational cost quadratic in the total number of spatio-temporal patches, severely limiting scalability. Motivated by this, we propose Selective Synergistic Learning (SSync). Instead of exhaustive patch-to-patch alignment, SSync prevents error propagation by selectively distilling only the most reliable cues: leveraging the encoder strictly for boundary refinement and the decoder for interior denoising. This is realized via a pseudo-labeling with linear complexity, eliminating the need for quadratic spatial comparisons. Also, to prevent the reinforcement of architectural biases like slot redundancy, we introduce a transitive pseudo-label merging that consolidates overlapping slots based on spatio-temporal activation consistency. Extensive studies demonstrate that SSync improves decomposition quality and serves as a versatile, plug-and-play module while also exhibiting exceptional robustness to slot configurations. Code is available at https://github.com/wjun0830/SSync. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

키워드

Object Discovery; Object Representation Learning; Self-Supervised Representation Learning; Video Object-Centric Learning
제목
Selective Synergistic Learning for Video Object-Centric Learning
저자
Moon, WonJun; Heo, Jae-Pil
DOI
10.1007/978-3-032-37383-0_2
발행일
2026
유형
Proceedings Paper
저널명
Lecture Notes in Computer Science
권
17016 LNCS
페이지
21 ~ 39