Craft: Cross-attentional flow transformer for robust optical flow
Optical flow estimation aims to find the 2D motion field by identifying corresponding pixels
between two images. Despite the tremendous progress of deep learning-based optical flow …
between two images. Despite the tremendous progress of deep learning-based optical flow …
Image-to-lidar self-supervised distillation for autonomous driving data
Segmenting or detecting objects in sparse Lidar point clouds are two important tasks in
autonomous driving to allow a vehicle to act safely in its 3D environment. The best …
autonomous driving to allow a vehicle to act safely in its 3D environment. The best …
Mst: Masked self-supervised transformer for visual representation
Transformer has been widely used for self-supervised pre-training in Natural Language
Processing (NLP) and achieved great success. However, it has not been fully explored in …
Processing (NLP) and achieved great success. However, it has not been fully explored in …
Siamese image modeling for self-supervised vision representation learning
Self-supervised learning (SSL) has delivered superior performance on a variety of
downstream vision tasks. Two main-stream SSL frameworks have been proposed, ie …
downstream vision tasks. Two main-stream SSL frameworks have been proposed, ie …
Self-supervised video pretraining yields robust and more human-aligned visual representations
N Parthasarathy, SM Eslami… - Advances in Neural …, 2023 - proceedings.neurips.cc
Humans learn powerful representations of objects and scenes by observing how they evolve
over time. Yet, outside of specific tasks that require explicit temporal understanding, static …
over time. Yet, outside of specific tasks that require explicit temporal understanding, static …
Croco: Self-supervised pre-training for 3d vision tasks by cross-view completion
Abstract Masked Image Modeling (MIM) has recently been established as a potent pre-
training paradigm. A pretext task is constructed by masking patches in an input image, and …
training paradigm. A pretext task is constructed by masking patches in an input image, and …
Self-paced contrastive learning for semi-supervised medical image segmentation with meta-labels
The contrastive pre-training of a recognition model on a large dataset of unlabeled data
often boosts the model's performance on downstream tasks like image classification …
often boosts the model's performance on downstream tasks like image classification …
Self-supervised contrastive learning with random walks for medical image segmentation with limited annotations
Medical image segmentation has seen significant progress through the use of supervised
deep learning. Hereby, large annotated datasets were employed to reliably segment …
deep learning. Hereby, large annotated datasets were employed to reliably segment …
Dense unsupervised learning for video segmentation
N Araslanov, S Schaub-Meyer… - Advances in neural …, 2021 - proceedings.neurips.cc
We present a novel approach to unsupervised learning for video object segmentation (VOS).
Unlike previous work, our formulation allows to learn dense feature representations directly …
Unlike previous work, our formulation allows to learn dense feature representations directly …
Embedding space interpolation beyond mini-batch, beyond pairs and beyond examples
S Venkataramanan, E Kijak… - Advances in neural …, 2024 - proceedings.neurips.cc
Mixup refers to interpolation-based data augmentation, originally motivated as a way to go
beyond empirical risk minimization (ERM). Its extensions mostly focus on the definition of …
beyond empirical risk minimization (ERM). Its extensions mostly focus on the definition of …