Cycle Consistency in Video Object-Centric Learning

• URL: http://arxiv.org/abs/2605.30211v1
• Date: Thu, 28 May 2026 16:45:24 GMT
• Title: Cycle Consistency in Video Object-Centric Learning
• Abstract summary: Self-supervised video Object-Centric Learning aims to discover distinct objects and associate them across time.<n>Cycle Consistency (CC) cannot naively or explicitly apply to the latent slot space of OCL.<n>We propose Implicit Cycle Consistency (ICC) which shifts the cycle-consistency constraint from the restrictive slot space to the continuous reconstruction manifold.
• Score: 33.833061023960546
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation [60.597357847359255]
  Video segmentation demands pixel-accurate object tracking across hundreds of frames under complex natural language queries.<n>Existing methods address this through token compression, yet typically operate on features lacking temporal context.<n>State-space models resolve this constraint, as their linear recurrence selectively conditions each token on temporal context at $mathcalO(T)$ cost compression to reduce.
  arXiv  Detail & Related papers  (2026-07-03T03:28:25Z)
• Rethinking Object-Centric Representations for Video Dynamics Modeling [17.157587526107598]
  Unsupervised video object tracking aims to decompose dynamic scenes into persistent, object-centric entities without manual annotations.<n>Many recent approaches rely on slot-based representations, where a fixed set of latent variables ("slots") represent individual objects across frames.<n>We propose STAITUS, a unified framework that explicitly disentangles each slot into appearance and geometric pose (position/scale).
  arXiv  Detail & Related papers  (2026-06-22T14:55:41Z)
• Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning [17.16289725621027]
  Unsupervised video object-centric learning aims to decompose dynamic scenes into persistent, object-level representations without supervision.<n>Existing slot-based methods struggle to maintain stable object identity in challenging settings such as rapid motion and partial occlusion.<n>We propose Dual-State Slot Attention (DSSA), a fully self-supervised framework that separates appearance from identity and reduces spurious updates from weakly matching slots.
  arXiv  Detail & Related papers  (2026-06-10T19:00:47Z)
• Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization [34.98521123729049]
  Slot-Slot Contrastive (SSC) loss has become the cornerstone for state-of-the-art (SOTA) video Object-Centric Learning (OCL) methods.<n>We propose a paradigm shift: temporal consistency is better enforced as an implicit model design rather than an explicit loss.
  arXiv  Detail & Related papers  (2026-05-29T16:28:21Z)
• CIG: Exploration via Conditional Information Gain [10.289348661352841]
  Intrinsic rewards for exploration in reinforcement learning condition on different contexts.<n> Conditional Information Gain (CIG) reward as a tractable surrogate.<n>We instantiate CIG in a model-based setting, where rollouts are short and within-rollout corrections remain largely unexplored.
  arXiv  Detail & Related papers  (2026-05-20T08:15:57Z)
• From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification [20.74226476678832]
  We propose SAGA-ReID, which reconstructs identity representations by aligning intermediate patch tokens with anchor vectors parameterized in CLIP's text embedding space.<n> Controlled experiments isolate the aggregation mechanism under two qualitatively distinct conditions.<n> Benchmark evaluations confirm consistent gains over CLIP-ReID across standard and occluded settings.
  arXiv  Detail & Related papers  (2026-04-24T03:37:21Z)
• Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment [83.56510119503265]
  Slot Attention (SA) with pretrained diffusion models has recently shown promise for object-centric learning (OCL), but suffers from slot entanglement and weak alignment between object slots and image content.<n>We propose Contrastive Object-centric Diffusion Alignment (CODA), a simple extension that (i) employs register slots to absorb residual attention and reduce interference between object slots, and (ii) applies a contrastive alignment loss to explicitly encourage slot-image correspondence.
  arXiv  Detail & Related papers  (2026-01-03T16:10:18Z)
• On the Alignment Between Supervised and Self-Supervised Contrastive Learning [8.71512981775656]
  Self-supervised contrastive learning (CL) has achieved remarkable empirical success.<n>Recent theory shows that the CL loss closely approximates a supervised surrogate, Negatives-Only Supervised Contrastive Learning (NSCL) loss.<n>We analyze the representation alignment of CL and NSCL models trained under shared randomness.
  arXiv  Detail & Related papers  (2025-10-09T23:01:42Z)
• Imputation-free and Alignment-free: Incomplete Multi-view Clustering Driven by Consensus Semantic Learning [65.75756724642932]
  In incomplete multi-view clustering, missing data induce prototype shifts within views and semantic inconsistencies across views.<n>We propose an IMVC framework, imputation- and alignment-free for consensus semantics learning (FreeCSL)<n>FreeCSL achieves more confident and robust assignments on IMVC task, compared to state-of-the-art competitors.
  arXiv  Detail & Related papers  (2025-05-16T12:37:10Z)
• Are We Done with Object-Centric Learning? [65.67948794110212]
  Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene.<n>With recent sample-efficient segmentation models, we can separate objects in the pixel space and encode them independently.<n>We address the OOD generalization challenge caused by spurious background cues through the lens of OCL.
  arXiv  Detail & Related papers  (2025-04-09T17:59:05Z)
• Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning [81.02648336552421]
  We propose a Multi-Constraint Consistency Learning approach to facilitate the staged enhancement of the encoder and decoder.<n>Self-adaptive feature masking and noise injection are designed in an instance-specific manner to perturb the features for robust learning of the decoder.<n> Experimental results on Pascal VOC2012 and Cityscapes datasets demonstrate that our proposed MCCL achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-23T03:21:33Z)
• Triplet Contrastive Learning for Unsupervised Vehicle Re-identification [55.445358749042384]
  Part feature learning is a critical technology for fine semantic understanding in vehicle re-identification. We propose a novel Triplet Contrastive Learning framework (TCL) which leverages cluster features to bridge the part features and global features.
  arXiv  Detail & Related papers  (2023-01-23T15:52:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.