Cover Image

Replacement Learning: Training Vision Tasks with Fewer Learnable Parameters

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yuming, Wang, Peizhe, Zhang, Shouxin, Guan, Dongzhi, Liu, Jiabin, Su, Junhao
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Replacement Learning: Training Neural Networks with Fewer Parameters
by: Zhang, Yuming, et al.
Published: (2026)

MLAAN: Scaling Supervised Local Learning with Multilaminar Leap Augmented Auxiliary Network
by: Zhang, Yuming, et al.
Published: (2024)

GSO-YOLO: Global Stability Optimization YOLO for Construction Site Detection
by: Zhang, Yuming, et al.
Published: (2024)

HPFF: Hierarchical Locally Supervised Learning with Patch Feature Fusion
by: Su, Junhao, et al.
Published: (2024)

Momentum Auxiliary Network for Supervised Local Learning
by: Su, Junhao, et al.
Published: (2024)

FQGA-single: Towards Fewer Training Epochs and Fewer Model Parameters for Image-to-Image Translation Tasks
by: Yang, Cho
Published: (2024)

Faster Multi-GPU Training with PPLL: A Pipeline Parallelism Framework Leveraging Local Learning
by: Guo, Xiuyuan, et al.
Published: (2024)

ELIP: Efficient Discriminative Language-Image Pre-training with Fewer Vision Tokens
by: Guo, Yangyang, et al.
Published: (2023)

PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks
by: Cui, Cheng, et al.
Published: (2026)

Learnable Sparsity for Vision Generative Models
by: Zhang, Yang, et al.
Published: (2024)

MAN++: Scaling Momentum Auxiliary Network for Supervised Local Learning in Vision Tasks
by: Su, Junhao, et al.
Published: (2025)

Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation
by: Wei, Zhixiang, et al.
Published: (2023)

FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters
by: Shao, Shitong, et al.
Published: (2026)

Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies
by: Zhu, Yuehua, et al.
Published: (2020)

Task-driven Image Fusion with Learnable Fusion Loss
by: Bai, Haowen, et al.
Published: (2024)

Geometric Parameter Estimations of Perovskite Solar Cells Based on Optical Simulations
by: Wang, Junhao
Published: (2025)

Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models
by: Chen, Shimin, et al.
Published: (2024)

Task-oriented Learnable Diffusion Timesteps for Universal Few-shot Learning of Dense Tasks
by: Oh, Changgyoon, et al.
Published: (2025)

Boosting Sclera Segmentation through Semi-supervised Learning with Fewer Labels
by: Wang, Guanjun, et al.
Published: (2025)

LeMeViT: Efficient Vision Transformer with Learnable Meta Tokens for Remote Sensing Image Interpretation
by: Jiang, Wentao, et al.
Published: (2024)

VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks
by: Chu, Xiangxiang, et al.
Published: (2024)

IV-tuning: Parameter-Efficient Transfer Learning for Infrared-Visible Tasks
by: Zhang, Yaming, et al.
Published: (2024)

LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images
by: Cheng, Yuzhou, et al.
Published: (2024)

PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer
by: Feng, Qian, et al.
Published: (2024)

On Learnable Parameters of Optimal and Suboptimal Deep Learning Models
by: Zheng, Ziwei, et al.
Published: (2024)

Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning
by: Lyu, Fan, et al.
Published: (2025)

Faster Training, Fewer Labels: Self-Supervised Pretraining for Fine-Grained BEV Segmentation
by: Busch, Daniel, et al.
Published: (2026)

Advancing Supervised Local Learning Beyond Classification with Long-term Feature Bank
by: Zhu, Feiyu, et al.
Published: (2024)

Polar R-CNN: End-to-End Lane Detection with Fewer Anchors
by: Wang, Shengqi, et al.
Published: (2024)

A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting
by: Zhuang, Junhao, et al.
Published: (2023)

SGW-based Multi-Task Learning in Vision Tasks
by: Zhang, Ruiyuan, et al.
Published: (2024)

DAPE: Dual-Stage Parameter-Efficient Fine-Tuning for Consistent Video Editing with Diffusion Models
by: Xia, Junhao, et al.
Published: (2025)

Evaluation of Safety Cognition Capability in Vision-Language Models for Autonomous Driving
by: Zhang, Enming, et al.
Published: (2025)

Depth-supervised NeRF: Fewer Views and Faster Training for Free
by: Deng, Kangle, et al.
Published: (2021)

EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation
by: Meng, Rang, et al.
Published: (2025)

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning
by: Zhong, Hanwen, et al.
Published: (2025)

Vision-based 3D occupancy prediction in autonomous driving: a review and outlook
by: Zhang, Yanan, et al.
Published: (2024)

Replace Anyone in Videos
by: Wang, Xiang, et al.
Published: (2024)

SliceLens: Fine-Grained and Grounded Error Slice Discovery for Multi-Instance Vision Tasks
by: Zhang, Wei, et al.
Published: (2025)

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
by: Bi, Jinhe, et al.
Published: (2024)