相关论文: Decoupled Prompt-Adapter Tuning for Continual Acti…
Recent advances in medical image segmentation have been driven by deep learning; however, most existing methods remain limited by modality-specific designs and exhibit poor adaptability to dynamic medical imaging scenarios. The Segment…
Visual Prompt Tuning (VPT) has proven effective for parameter-efficient adaptation of pre-trained vision models to downstream tasks by inserting task-specific learnable prompt tokens. Despite its empirical success, a comprehensive…
This paper presents a novel attention-based algorithm for achieving adaptive computation called DACT, which, unlike existing ones, is end-to-end differentiable. Our method can be used in conjunction with many networks; in particular, we…
Recent advances in decentralized deep learning algorithms have demonstrated cutting-edge performance on various tasks with large pre-trained models. However, a pivotal prerequisite for achieving this level of competitiveness is the…
Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data,…
Agile humanoid locomotion in complex 3D en- vironments requires balancing perceptual fidelity with com- putational efficiency, yet existing methods typically rely on rigid sensing configurations. We propose ADAPT (Adaptive dual-projection…
Visual prompt tuning (VPT) is a promising solution incorporating learnable prompt tokens to customize pre-trained models for downstream tasks. However, VPT and its variants often encounter challenges like prompt initialization, prompt…
The auditory system plays a substantial role in shaping the overall human perceptual experience. While prevailing large language models (LLMs) and visual language models (VLMs) have shown their promise in solving a wide variety of language…
Forecasting 3D human motion is an important embodiment of fine-grained understanding and cognition of human behavior by artificial agents. Current approaches excessively rely on implicit network modeling of spatiotemporal relationships and…
Cross-domain object detection is more challenging than object classification since multiple objects exist in an image and the location of each object is unknown in the unlabeled target domain. As a result, when we adapt features of…
Distribution shift is a common challenge in medical images obtained from different clinical centers, significantly hindering the deployment of pre-trained semantic segmentation models in real-world applications across multiple domains.…
Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment. Recent works employ LLMs-as-agents in broadly two ways: iteratively determining the next…
The learning rate is a crucial hyperparameter in deep learning, with its ideal value depending on the problem and potentially changing during training. In this paper, we investigate the practical utility of adaptive learning rate mechanisms…
Modern multi-object tracking (MOT) systems usually model the trajectories by associating per-frame detections. However, when camera motion, fast motion, and occlusion challenges occur, it is difficult to ensure long-range tracking or even…
This article proposes a novel attention-based body pose encoding for human activity recognition that presents a enriched representation of body-pose that is learned. The enriched data complements the 3D body joint position data and improves…
Visual prompt tuning (VPT), i.e., fine-tuning some lightweight prompt tokens, provides an efficient and effective approach for adapting pre-trained models to various downstream tasks. However, most prior art indiscriminately uses a fixed…
Out-of-distribution (OOD) detection is essential for ensuring the robustness of machine learning models by identifying samples that deviate from the training distribution. While traditional OOD detection has primarily focused on…
Recent developments have underscored the critical role of \textit{differential privacy} (DP) in safeguarding individual data for training machine learning models. However, integrating DP oftentimes incurs significant model performance…
Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the…
Temporal action detection aims to locate and classify actions in untrimmed videos. While recent works focus on designing powerful feature processors for pre-trained representations, they often overlook the inherent noise and redundancy…