相关论文: DualCP: Rehearsal-Free Domain-Incremental Learning…

Class-incremental learning (CIL) enables continuous learning of new classes while mitigating catastrophic forgetting of old ones. For the performance breakthrough of CIL, it is essential yet challenging to effectively refine past knowledge…

Semantic segmentation on driving-scene images is vital for autonomous driving. Although encouraging performance has been achieved on daytime images, the performance on nighttime images are less satisfactory due to the insufficient exposure…

Domain Incremental Learning (DIL) is a continual learning sub-branch that aims to address never-ending arrivals of new domains without catastrophic forgetting problems. Despite the advent of parameter-efficient fine-tuning (PEFT)…

Surgical action planning requires predicting future instrument-verb-target triplets for real-time assistance. While teleoperated robotic surgery provides natural expert demonstrations for imitation learning (IL), reinforcement learning (RL)…

3D perception plays a crucial role in real-world applications such as autonomous driving, robotics, and AR/VR. In practical scenarios, 3D perception models must continuously adapt to new data and emerging object categories, but retraining…

Following language instructions to navigate in unseen environments is a challenging task for autonomous embodied agents. With strong representation capabilities, pretrained vision-and-language models are widely used in VLN. However, most of…

Recent studies have shown that Transformers can perform in-context reinforcement learning (RL) by imitating existing RL algorithms, enabling sample-efficient adaptation to unseen tasks without parameter updates. However, these models also…

In-context learning (ICL) has proven highly effective across diverse large language model (LLM) tasks. However, its potential for enhancing tasks that demand step-by-step logical deduction, such as mathematical reasoning, remains…

Cross-domain recommendation (CDR) aims to improve recommendation accuracy in sparse domains by transferring knowledge from data-rich domains. However, existing CDR approaches often assume that user-item interaction data across domains is…

Image-point class incremental learning helps the 3D-points-vision robots continually learn category knowledge from 2D images, improving their perceptual capability in dynamic environments. However, some incremental learning methods address…

Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain-adaptive pre-training (or continual DAP-training). Existing…

Large language models have achieved impressive performance across diverse tasks. However, their tendency to produce overconfident and factually incorrect outputs, known as hallucinations, poses risks in real world applications. Conformal…

We address the Continual Learning (CL) problem, wherein a model must learn a sequence of tasks from non-stationary distributions while preserving prior knowledge upon encountering new experiences. With the advancement of foundation models,…

Self-supervised learning (SSL) methods based on the instance discrimination tasks with InfoNCE have achieved remarkable success. Despite their success, SSL models often struggle to generate effective representations for unseen-domain data.…

Prompt learning is one of the most effective and trending ways to adapt powerful vision-language foundation models like CLIP to downstream datasets by tuning learnable prompt vectors with very few samples. However, although prompt learning…

Contrastive Language-Image Pretraining (CLIP) model has exhibited remarkable efficacy in establishing cross-modal connections between texts and images, yielding impressive performance across a broad spectrum of downstream applications…

Prompt learning has emerged as a valuable technique in enhancing vision-language models (VLMs) such as CLIP for downstream tasks in specific domains. Existing work mainly focuses on designing various learning forms of prompts, neglecting…

In recent studies on domain adaptation, significant emphasis has been placed on the advancement of learning shared knowledge from a source domain to a target domain. Recently, the large vision-language pre-trained model, i.e., CLIP has…

While deep neural networks demonstrate state-of-the-art performance on a variety of learning tasks, their performance relies on the assumption that train and test distributions are the same, which may not hold in real-world applications.…

We present a novel unsupervised domain adaptation method for semantic segmentation that generalizes a model trained with source images and corresponding ground-truth labels to a target domain. A key to domain adaptive semantic segmentation…