This paper proposes a deep video compression method to simultaneously encode multiple frames with Frame-Conv3D and differential modulation.
We propose to feed different data samples with varying quantization schemes to achieve a data-dependent dynamic inference, at a fine-grained layer level.
It is hard to replicate these approaches in trajectory forecasting due to the lack of adequate trajectory data (e. g., 34K samples in the nuScenes dataset).
Moreover, to properly evaluate an IBP model with offline datasets, we propose a Shapley-value-based metric to testify if the prediction model satisfies the inherent temporal independence of an interventional distribution.
To address these issues, we propose a novel approach to avoid KL vanishing and induce an interpretable interactive latent space with pseudo labels.
The exponentially large discrete search space in mixed-precision quantization (MPQ) makes it hard to determine the optimal bit-width for each layer.
In recent years much effort has been devoted to applying neural models to the task of natural language generation.
In this work, we argue that one of the typical formulations of VAEs in multi-agent modeling suffers from an issue we refer to as social posterior collapse, i. e., the model is prone to ignoring historical social context when predicting the future trajectory of an agent.
Reinforcement Learning (RL) has been shown effective in domains where the agent can learn policies by actively interacting with its operating environment.
Explainability is essential for autonomous vehicles and other robotics systems interacting with humans and other objects during operation.
To accelerate deep CNN models, this paper proposes a novel spatially adaptive framework that can dynamically generate pixel-wise sparsity according to the input image.
Current methods for long-term trajectory prediction cannot guarantee the physical feasibility of predicted distribution.
Learning from demonstrations is a popular tool for accelerating and reducing the exploration requirements of reinforcement learning.
Although deep reinforcement learning (deep RL) methods have lots of strengths that are favorable if applied to autonomous driving, real deep RL applications in autonomous driving have been slowed down by the modeling gap between the source (training) domain and the target (deployment) domain.