Self-supervised Learning of Contextualized Local Visual Embeddings
Not on the map. Why?
Abstract (arXiv)
We present Contextualized Local Visual Embeddings (CLoVE), a self-supervised convolutional-based method that learns representations suited for dense prediction tasks. CLoVE deviates from current methods and optimizes a single loss function that operates at the level of contextualized local embeddings learned from output feature maps of convolution neural network (CNN) encoders. To learn contextualized embeddings, CLoVE proposes a normalized mult-head self-attention layer that combines local features from different parts of an image based on similarity. We extensively benchmark CLoVE's pre-trained representations on multiple datasets. CLoVE reaches state-of-the-art performance for CNN-based architectures in 4 dense prediction downstream tasks, including object detection, instance segmentation, keypoint detection, and dense pose estimation.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 37 of its 40 references that are in the map. First posted on arXiv 1 Oct 2023.
Builds on
37 of 40 references.
References · 37
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2017Mask R-CNNcited by 7,259
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
- 2022Generative Adversarial Networkscited by 5,603
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
25 more
- 2020Exploring Simple Siamese Representation Learningcited by 2,853
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
- 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
- 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
- 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
- 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
- 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
- 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
- 2020What Makes for Good Views for Contrastive Learning?cited by 843
- 2017Large Batch Training of Convolutional Networkscited by 529
- 2019Self-labelling via simultaneous clustering and representation learningcited by 525
- 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
- 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
- 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
- 2018Acquisition of Localization Confidence for Accurate Object Detectioncited by 174
- 2020Unsupervised Learning of Dense Visual Representationscited by 147
- 2022VICRegL: Self-Supervised Learning of Local Visual Featurescited by 118
- 2021Region Similarity Representation Learningcited by 96
- 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
- 2021Solving Inefficiency of Self-supervised Representation Learningcited by 41
- 2021Exploring Set Similarity for Dense Self-supervised Representation Learningcited by 29
- 2022CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentationcited by 26
- 2021Representation Learning via Consistent Assignment of Views to Clusterscited by 8
- 2022InsCon:Instance Consistency Feature Representation via Self-Supervised Learningcited by 8
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.