Search Results for author:
Found 10 papers, 3 papers with code
Emerging Property of Masked Token for Effective Pre-training
Initially, we delve into an exploration of the inherent properties that a masked token ought to possess.
Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training
In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Modeling (MIM) approaches by prioritizing token salience.
Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning
Recent vision-based reinforcement learning (RL) methods have found extracting high-level features from raw pixels with self-supervised learning to be effective in learning policies.
Environment Agnostic Representation for Visual Reinforcement Learning
Generalization capability of vision-based deep reinforcement learning (RL) is indispensable to deal with dynamic environment changes that exist in visual observations.
Sequential Cross Attention Based Multi-task Learning
The cross-task attention module (CTAM) is first applied to facilitate the exchange of relevant information between the multiple task features of the same scale.
KNN Local Attention for Image Restoration
In this way, the pair-wise operation establishes non-local connectivity while maintaining the desired properties of the local attention, i. e., inductive bias of locality and linear complexity to input resolution.
Self-Supervised Structured Representations for Deep Reinforcement Learning
The proposed method imposes similarity constraints on the three latent volumes; warped query representations by estimated flows, predicted target representations from the transition model, and target representations of future state.
Weakly-Supervised Learning of Disentangled and Interpretable Skills for Hierarchical Reinforcement Learning
Given the latent representations as skills, a skill-based policy network is trained to generate similar trajectories to the learned decoder of the trajectory VAE.
Pseudo Label-Guided Multi Task Learning for Scene Understanding
More importantly, the pseudo depth labels serve to impose a cross-view consistency on the estimated monocular depth and segmentation maps of two views.
Adaptive confidence thresholding for monocular depth estimation
To cope with the prediction error of the confidence map itself, we also leverage the threshold network that learns the threshold dynamically conditioned on the pseudo depth maps.
