Models pre-trained on large-scale datasets are often finetuned to suppor...
Learning policies from fixed offline datasets is a key challenge to scal...
Camera pose estimation is a key step in standard 3D reconstruction pipel...
Obtaining photorealistic reconstructions of objects from sparse views is...
Despite their recent success, deep neural networks continue to perform p...
Offline reinforcement learning leverages large datasets to train policie...
Deep Metric Learning (DML) aims to find representations suitable for
zer...
Variational auto-encoders (VAEs) are a powerful approach to unsupervised...
Offline reinforcement learning proposes to learn policies from large
col...
We present an approach for physical imitation from human videos for robo...
Contrastive learning is an effective method for learning visual
represen...
While improvements in deep learning architectures have played a crucial ...
Deep Neural Networks have shown great promise on a variety of downstream...
The use of past experiences to accelerate temporal difference (TD) learn...
Visual Similarity plays an important role in many computer vision
applic...
Visual Similarity plays an important role in many computer vision
applic...
Although deep learning models have achieved state-of-the-art performance...
Convolutional Neural Networks (CNNs) have shown impressive performance i...
Deep Metric Learning (DML) is arguably one of the most influential lines...
We introduce a simple (one line of code) modification to the Generative
...
Recent work by Brock et al. (2018) suggests that Generative Adversarial
...
Active learning aims to develop label-efficient algorithms by sampling t...
Many approaches in generalized zero-shot learning rely on cross-modal ma...