Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting

Abstract

Cross-domain crowd counting (CDCC) is a hot topic due to its importance in public safety. The purpose of CDCC is to alleviate the domain shift between the source and target domain. Recently, typical methods attempt to extract domain-invariant features via image translation and adversarial learning. When it comes to specific tasks, we find that the domain shifts are reflected on model parameters' differences. To describe the domain gap directly at the parameter-level, we propose a Neuron Linear Transformation (NLT) method, exploiting domain factor and bias weights to learn the domain shift. Specifically, for a specific neuron of a source model, NLT exploits few labeled target data to learn domain shift parameters. Finally, the target neuron is generated via a linear transformation. Extensive experiments and analysis on six real-world datasets validate that NLT achieves top performance compared with other domain adaptation methods. An ablation study also shows that the NLT is robust and more effective than supervised and fine-tune training. Code is available at: \url{https://github.com/taohan10200/NLT}.

arXiv commentaccepted by IEEE T-NNLS

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• A Simple Neural Attentive Meta-Learner
• Deep Visual Attention Prediction
• On First-Order Meta-Learning Algorithms
• NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
• HA-CCN: Hierarchical Attention-based Crowd Counting Network
• Quadruplet Network with One-Shot Learning for Fast Visual Object Tracking
• Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid
• PaDNet: Pan-Density Crowd Counting
• C^3 Framework: An Open-source PyTorch Code for Crowd Counting
• Clickstream analysis for crowd-based object segmentation with confidence
• Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning

Cited by in corpus (9)

• Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation
• Learning causal representations for robust domain adaptation
• Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
• Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting
• Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting
• AdaTreeFormer: Few Shot Domain Adaptation for Tree Counting from a Single High-Resolution Image
• Fine-grained Domain Adaptive Crowd Counting via Point-derived Segmentation
• AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
• A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View