Unsupervised Learning of Dense Visual Representations
Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e., compositions of data augmentation) of the same image. However, many visual understanding tasks require dense (pixel-level) representations. In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. VADeR learns pixelwise representations by forcing local features to remain constant over different viewing conditions. Specifically, this is achieved through pixel-level contrastive learning: matching features (that is, features that describes the same location of the scene on different views) should be close in an embedding space, while non-matching features should be apart. VADeR provides a natural representation for dense prediction tasks and transfers well to downstream tasks. Our method outperforms ImageNet supervised pretraining (and strong unsupervised baselines) in multiple dense prediction tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningData AugmentationRepresentation LearningSelf-Supervised LearningSimilar Papers 제목 키워드 기반
DIP: Unsupervised Dense In-Context Post-training of Visual Representations
We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understanding. Unlike prior approaches that rely …
GPUMeta-LearningScene UnderstandingDense Video Captioning Using Unsupervised Semantic Information
We introduce a method to learn unsupervised semantic visual information based on the premise that complex events can be decomposed into simpler events and that these simple events are shared across several complex events…
Dense Video CaptioningVideo CaptioningVirTex: Learning Visual Representations from Textual Annotations
The de-facto approach to many vision tasks is to start from pretrained visual representations, typically learned via supervised training on ImageNet. Recent methods have explored unsupervised pretraining to scale to vast…
General ClassificationImage Captioningimage-classificationImage Classification+4Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning has yet to be fully unleashed, as curre…
Contrastive Learningobject-detectionObject DetectionRepresentation Learning+1Dense Siamese Network for Dense Unsupervised Learning
This paper presents Dense Siamese Network (DenseSiam), a simple unsupervised learning framework for dense prediction tasks. It learns visual representations by maximizing the similarity between two views of one image wit…
Self-Supervised LearningSemantic SegmentationUnsupervised Semantic Segmentation