Understanding Self-Supervised Pretraining with Part-Aware Representation Learning
In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised representation pretraining methods learn part-aware representations. The study is mainly motivated by that random views, used in contrastive learning, and random masked (visible) patches, used in masked image modeling, are often about object parts. We explain that contrastive learning is a part-to-whole task: the projection layer hallucinates the whole object representation from the object part representation learned from the encoder, and that masked image modeling is a part-to-part task: the masked patches of the object are hallucinated from the visible patches. The explanation suggests that the self-supervised pretrained encoder is required to understand the object part. We empirically compare the off-the-shelf encoders pretrained with several representative methods on object-level recognition and part-level recognition. The results show that the fully-supervised model outperforms self-supervised models for object-level recognition, and most self-supervised contrastive learning and masked image modeling methods outperform the fully-supervised method for part-level recognition. It is observed that the combination of contrastive learning and masked image modeling further improves the performance.
Code (1)
Tasks
Contrastive LearningObjectRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TIPS: Text-Image Pretraining with Spatial Awareness
While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-…
Depth EstimationImage CaptioningRepresentation LearningSelf-Supervised Learning+1Location-Aware Self-Supervised Transformers for Semantic Segmentation
Pixel-level labels are particularly expensive to acquire. Hence, pretraining is a critical step to improve models on a task like semantic segmentation. However, prominent algorithms for pretraining neural networks use im…
Contrastive Learningimage-classificationImage ClassificationSegmentation+2Hierarchical Self-supervised Representation Learning for Movie Understanding
Most self-supervised video representation learning approaches focus on action recognition. In contrast, in this paper we focus on self-supervised video learning for movie understanding and propose a novel hierarchical se…
Action RecognitionContrastive LearningRepresentation LearningOccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
We introduce a self-supervised pretraining method, called OccFeat, for camera-only Bird's-Eye-View (BEV) segmentation networks. With OccFeat, we pretrain a BEV network via occupancy prediction and feature distillation ta…
BEV SegmentationPredictionSegmentationSemantic SegmentationNucleus-aware Self-supervised Pretraining Using Unpaired Image-to-image Translation for Histopathology Images
Self-supervised pretraining attempts to enhance model performance by obtaining effective features from unlabeled data, and has demonstrated its effectiveness in the field of histopathology images. Despite its success, fe…
DiversityImage-to-Image TranslationInstance SegmentationMultiple Instance Learning+2