The Impact of Semantic Pairs on Self-Supervised Representation Learning
Instance discrimination learns visual representations by treating different augmented views of the same image as positive pairs. While this encourages invariance to handcrafted transformations, same-image positives can preserve nuisance correlations such as background, texture, illumination, and object-specific details. Semantic positive pairs, i.e., different same-class instances, may reduce these correlations by presenting objects across diverse contexts. However, previous studies often combine semantic pairs with augmented positives or false neighbors (i.e., incorrectly mapped semantic pairs), making it difficult to isolate the effect of semantic pairing. We present a controlled empirical study of semantic positive pairs for self-supervised representation learning. From ImageNet-1K, we construct two matched subsets: an augmented-pair baseline and a manually curated semantic-pair dataset with the same class composition and training-pair count. We use these datasets to compare representative contrastive and non-contrastive SSL methods under matched training conditions. Across transfer learning and object detection evaluations, semantic-pair pretraining consistently improves generalisation over augmented-pair pretraining. Additional ablations show that semantic pairs induce invariances beyond the standard transformation pipeline. Among the evaluated methods, contrastive learning benefits most strongly from semantic pairs, with SimCLR showing the largest relative improvement. These results clarify the role of semantic positive pairs in SSL and provide guidance for selecting and designing frameworks that can exploit semantic pair information effectively
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningContrastive LearningTransfer LearningObject DetectionSimilar Papers 제목 키워드 기반
MSR: Making Self-supervised learning Robust to Aggressive Augmentations
Most recent self-supervised learning methods learn visual representation by contrasting different augmented views of images. Compared with supervised learning, more aggressive augmentations have been introduced to furthe…
MemorizationSelf-Supervised LearningEmbodied-Symbolic Contrastive Graph Self-Supervised Learning for Molecular Graphs
Dual embodied-symbolic concept representations are the foundation for deep learning and symbolic AI integration. We discuss the use of dual embodied-symbolic concept representations for molecular graph representation lea…
Graph Representation LearningRepresentation LearningSelf-Supervised LearningGroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
Self-supervised 3D representation learning aims to learn effective representations from large-scale unlabeled point clouds. Most existing approaches adopt point discrimination as the pretext task, which assigns matched p…
Contrastive LearningRepresentation LearningScene UnderstandingTransfer LearningSelf-Supervised Speech Representations are More Phonetic than Semantic
Self-supervised speech models (S3Ms) have become an effective backbone for speech applications. Various analyses suggest that S3Ms encode linguistic properties. In this work, we seek a more fine-grained analysis of the w…
intent-classificationIntent ClassificationSemantic SimilaritySemantic Textual SimilarityText Transformations in Contrastive Self-Supervised Learning: A Review
Contrastive self-supervised learning has become a prominent technique in representation learning. The main step in these methods is to contrast semantically similar and dissimilar pairs of samples. However, in the domain…
Contrastive LearningRepresentation LearningSelf-Supervised LearningSentence