DIOD: Self-Distillation Meets Object Discovery
Instance segmentation demands substantial labeling resources. This has prompted increased interest to explore the object discovery task as an unsupervised alternative. In particular promising results were achieved in localizing instances using motion supervision only. However the motion signal introduces complexities due to its inherent noise and sparsity which constrains the effectiveness of current methodologies. In the present paper we propose DIOD (self DIstillation meets Object Discovery) the first method that places the motion-guided object discovery within a framework of continuous improvement through knowledge distillation providing solutions to existing limitations (i) DIOD robustly eliminates the noise present in the exploited motion maps providing accurate motion-supervision (ii) DIOD leverages the discovered objects within an iterative pseudo-labeling framework enriching the initial motion-supervision with static objects which results in a cost-efficient increase in performance. Through experiments on synthetic and real-world datasets we demonstrate the benefits of bridging the gap between object discovery and distillation by significantly improving the state-of-the-art. This enhancement is also sustained across other demanding metrics so far reserved for supervised tasks.
Code (1)
Tasks
Instance SegmentationKnowledge DistillationObjectObject DiscoverySemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend on feature distillation to prevent forge…
class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+2Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D Motion
Object discovery, which refers to the task of localizing objects without human annotations, has gained significant attention in 2D image analysis. However, despite this growing interest, it remains under-explored in …
Multi-object discoveryObjectObject DiscoveryObject LocalizationxMOD: Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D motion
Object discovery, which refers to the task of localizing objects without human annotations, has gained significant attention in 2D image analysis. However, despite this growing interest, it remains under-explored in 3D d…
Multi-object discoveryObjectObject DiscoveryObject LocalizationSD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERT
Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a new era of spoken language processing. Yet, the discovered units often remain in phonetic space and the units beyond phonemes are l…
Language ModelingLanguage ModellingSelf-Supervised LearningSentenceIdentity-preserving Distillation Sampling by Fixed-Point Iterator
Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions. However, SDS often suffers from blurri…
NeRF