Pyra: Parallel yielding re-activation for training-inference efficient task adaptation
Recently, the scale of transformers has grown rapidly, which introduces considerable
challenges in terms of training overhead and inference efficiency in the scope of task …
challenges in terms of training overhead and inference efficiency in the scope of task …
Parameter efficient fine-tuning via cross block orchestration for segment anything model
Parameter-efficient fine-tuning (PEFT) is an effective methodology to unleash the potential of
large foundation models in novel scenarios with limited training data. In the computer vision …
large foundation models in novel scenarios with limited training data. In the computer vision …
Image compression for machine and human vision with spatial-frequency adaptation
Image compression for machine and human vision (ICMH) has gained increasing attention
in recent years. Existing ICMH methods are limited by high training and storage overheads …
in recent years. Existing ICMH methods are limited by high training and storage overheads …
Revisiting the power of prompt for visual tuning
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 …
customize pre-trained models for downstream tasks. However, VPT and its variants often …
V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark
Parameter-efficient transfer learning (PETL) methods show promise in adapting a pre-
trained model to various downstream tasks while training only a few parameters. In the …
trained model to various downstream tasks while training only a few parameters. In the …
LSPT: Long-term Spatial Prompt Tuning for Visual Representation Learning
S Mo, Y Wang, X Luo, D Li - arxiv preprint arxiv:2402.17406, 2024 - arxiv.org
Visual Prompt Tuning (VPT) techniques have gained prominence for their capacity to adapt
pre-trained Vision Transformers (ViTs) to downstream visual tasks using specialized …
pre-trained Vision Transformers (ViTs) to downstream visual tasks using specialized …
VioLET: Vision-Language Efficient Tuning with Collaborative Multi-modal Gradients
Parameter-Efficient Tuning (PET) has emerged as a leading advancement in both Natural
Language Processing and Computer Vision, enabling efficient accommodation of …
Language Processing and Computer Vision, enabling efficient accommodation of …
Learning dual updatable memory modules for video anomaly detection
L Zhang, S Li, Y Cheng, X Luo, X Liu - Multimedia Systems, 2025 - Springer
We propose a novel video anomaly detection method that leverages two updatable memory
modules to learn and update prototypical patterns of normal and abnormal data within an …
modules to learn and update prototypical patterns of normal and abnormal data within an …
iVPT: Improving Task-relevant Information Sharing in Visual Prompt Tuning by Cross-layer Dynamic Connection
Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-
trained vision transformers to various downstream tasks. However, most existing solutions …
trained vision transformers to various downstream tasks. However, most existing solutions …
BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation
Pre-training followed by full fine-tuning has gradually been substituted by Parameter-
Efficient Tuning (PET) in the field of computer vision. PET has gained popularity, especially …
Efficient Tuning (PET) in the field of computer vision. PET has gained popularity, especially …