Related papers: HyCoRA: Hyper-Contrastive Role-Adaptive Learning f…

Reinforcement learning (RL) exhibits remarkable potential in addressing autonomous driving tasks. However, it is difficult to train a sample-efficient and safe policy in complex scenarios. In this article, we propose a novel hierarchical…

The substantial computational demands of modern large-scale deep learning present significant challenges for efficient training and deployment. Recent research has revealed a widespread phenomenon wherein deep networks inherently learn…

Learning long-range behaviors on complex high-dimensional agents is a fundamental problem in robot learning. For such tasks, we argue that transferring learned information from a morphologically simpler agent can massively improve the…

Context-aware methods achieved great success in supervised scene text recognition via incorporating semantic priors from words. We argue that such prior contextual information can be interpreted as the relations of textual primitives due to…

Transfer learning is a useful technique for achieving improved performance and reducing training costs by leveraging the knowledge gained from source tasks and applying it to target tasks. Assessing the effectiveness of transfer learning…

Zero-shot coordination problem in multi-agent reinforcement learning (MARL), which requires agents to adapt to unseen agents, has attracted increasing attention. Traditional approaches often rely on the Self-Play (SP) framework to generate…

Multimodal models integrating natural language and visual information have substantially improved generalization of representation models. However, their effectiveness significantly declines in real-world situations where certain modalities…

Utilizing deep learning models to learn part-based representations holds significant potential for interpretable-by-design approaches, as these models incorporate latent causes obtained from feature representations through simple addition.…

Existing architectures of multi-domain learning have two types of adapters: shared LoRA for all domains and domain-specific LoRA for each particular domain. However, it remains unclear whether this structure effectively captures…

Contrastive learning has shown to learn better quality representations than models trained using cross-entropy loss. They also transfer better to downstream datasets from different domains. However, little work has been done to explore the…

Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline. Whilst adversarial adaptation significantly…

We develop a novel transfer learning framework to tackle the challenge of limited training data in image reconstruction problems. The proposed framework consists of two training steps, both of which are formed as bi-level optimizations. In…

Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…

Irregular scene text recognition has attracted much attention from the research community, mainly due to the complexity of shapes of text in natural scene. However, recent methods either rely on shape-sensitive modules such as bounding box…

Self-attention has emerged as a core component of modern neural architectures, yet its theoretical underpinnings remain elusive. In this paper, we study self-attention through the lens of interacting entities, ranging from agents in…

Mutual adaptation can significantly enhance overall task performance in human-robot co-transportation by integrating both the robot's and human's understanding of the environment. While human modeling helps capture humans' subjective…

Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods. Supervised contrastive learning has also been shown to outperform its cross-entropy…

This paper presents a new multitask learning framework that learns a shared representation among the tasks, incorporating both task and feature clusters. The jointly-induced clusters yield a shared latent subspace where task relationships…

Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models for each new task is usually impractical. Multi-task…

Contrastive learning has been proven beneficial for self-supervised skeleton-based action recognition. Most contrastive learning methods utilize carefully designed augmentations to generate different movement patterns of skeletons for the…