Asia
IDRNet: Intervention-Driven Relation Network for Semantic Segmentation
With the built relation matrix and semantic-level representations, pixel representations can be augmented for pixel prediction.
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
In this work, we present a dual-stage low-bit post-training quantization (PTQ) method for image super-resolution, namely 2DQuant, which achieves efficient and accurate SR under low-bit quantization.
Model Sparsity Can Simplify Machine Unlearning
This leads to a new MU paradigm, termed prune first, then unlearn, which infuses a sparse model prior into the unlearning process.
Unleash the Potential of Image Branch for Cross-modal 3D Object Detection
However, existing cross-modal 3D detectors do not fully utilize the image domain information to address the bottleneck issues of the LiDAR-based detectors.
The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space Hongyao Tang
Deep Reinforcement Learning (DRL) is far from well understood, although its great potential has been demonstrated with a lot of achievements in different practical problems [Badia et al., 2020, Shah et al., 2022, Fawzi et al., 2022, Degrave et al., 2022, OpenAI, 2022]. Consistent efforts are made to gain a better understanding of the learning dynamics of RL agents.
Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills Denis Blessing
Imitation learning uses data for training policies to solve complex tasks.
