Search Results for author: Samyakh Tukra

Found 3 papers, 2 papers with code

Improving Visual Representation Learning through Perceptual Understanding

1 code implementation CVPR 2023 Samyakh Tukra, Frederick Hoffman, Ken Chatfield

We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features.

Representation Learning Self-Supervised Image Classification

Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation

no code implementations18 Dec 2019 Tianhong Dai, Kai Arulkumaran, Tamara Gerbert, Samyakh Tukra, Feryal Behbahani, Anil Anthony Bharath

Furthermore, even with an improved saliency method introduced in this work, we show that qualitative studies may not always correspond with quantitative measures, necessitating the combination of inspection tools in order to provide sufficient insights into the behaviour of trained agents.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.