Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite
their success, ViTs lack inductive biases, which can make it difficult to train
them with limited data. To address this challenge, prior studies suggest
training ViTs with self-supervised learning (SSL) and fine-tuning sequentially.
However, we observe that jointly optimizing ViTs for the primary task and a
Self-Supervised Auxiliary Task (SSAT) is surprisingly beneficial when the
amount of training data is limited. We explore the appropriate SSL tasks that
can be optimized alongside the primary task, the training schemes for these
tasks, and the data scale at which they can be most effective. Our findings
reveal that SSAT is a powerful technique that enables ViTs to leverage the
unique characteristics of both the self-supervised and primary tasks, achieving
better performance than typical ViTs pre-training with SSL and fine-tuning
sequentially. Our experiments, conducted on 10 datasets, demonstrate that SSAT
significantly improves ViT performance while reducing carbon footprint. We also
confirm the effectiveness of SSAT in the video domain for deepfake detection,
showcasing its generalizability. Our code is available at
this https URL

Vision Transformers (ViTs) 使用自我监督学习 (SSAT) 作为辅助任务与主任务同时进行联合优化，以在有限的数据量下取得更好的性能表现，此方法能帮助 ViTs 充分利用自我监督任务和主任务的独特特点，展现出优于传统的 ViTs 预训练与后续微调的效果，并在 10 个数据集的实验证明了 SSAT 的显著性提升并减少了碳足迹，同时在视频领域的 Deepfake 检测上也验证了其普遍适用性。

有限数据，无限潜力：ViT 与遮蔽自编码器增强的研究

Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked  Autoencoders

Recent approaches have utilized self-supervised auxiliary tasks as
representation learning to improve the performance and sample efficiency of
vision-based reinforcement learning algorithms in single-agent settings.
However, in multi-agent reinforcement learning (MARL), these techniques face
challenges because each agent only receives partial observation from an
environment influenced by others, resulting in correlated observations in the
agent dimension. So it is necessary to consider agent-level information in
representation learning for MARL. In this paper, we propose an effective
framework called \textbf{M}ulti-\textbf{A}gent \textbf{M}asked
\textbf{A}ttentive \textbf{C}ontrastive \textbf{L}earning (MA2CL), which
encourages learning representation to be both temporal and agent-level
predictive by reconstructing the masked agent observation in latent space.
Specifically, we use an attention reconstruction model for recovering and the
model is trained via contrastive learning. MA2CL allows better utilization of
contextual information at the agent level, facilitating the training of MARL
agents for cooperation tasks. Extensive experiments demonstrate that our method
significantly improves the performance and sample efficiency of different MARL
algorithms and outperforms other methods in various vision-based and
state-based scenarios. Our code can be found in
https://github.com/ustchlsong/MA2CL

本文提出了一个名为 MA2CL 的新方法，通过使用掩码代理观察在潜在空间中重建模型，并使用对比学习对模型进行训练，鼓励学习表示是同时具有时间性和代理级别预测性的，以提高多代理强化学习的效率和样本效率，扩大了环境中代理级别的上下文信息的应用。

MA2CL: 多智能体强化学习的遮蔽式关注对比学习

MA2CL:Masked Attentive Contrastive Learning for Multi-Agent  Reinforcement Learning

Deep reinforcement learning (DRL) has achieved great successes in recent
years with the help of novel methods and higher compute power. However, there
are still several challenges to be addressed such as convergence to locally
optimal policies and long training times. In this paper, firstly, we augment
Asynchronous Advantage Actor-Critic (A3C) method with a novel self-supervised
auxiliary task, i.e. \emph{Terminal Prediction}, measuring temporal closeness
to terminal states, namely A3C-TP. Secondly, we propose a new framework where
planning algorithms such as Monte Carlo tree search or other sources of
(simulated) demonstrators can be integrated to asynchronous distributed DRL
methods. Compared to vanilla A3C, our proposed methods both learn faster and
converge to better policies on a two-player mini version of the Pommerman game.

本文介绍了一种新的深度强化学习方法 Asynchronous Advantage Actor-Critic (A3C-TP)，并提出一种新的框架，将规划算法和异步分布式深度强化学习方法相结合，相对于传统方法，提高了学习速度和收敛策略的能力。