ProtoGMM: Multi-prototype Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation
원문 초록
Domain adaptive semantic segmentation aims to generate accurate and dense predictions for an unlabeled target domain by leveraging a supervised model trained on a labeled source domain. The prevalent self-training approach involves retraining the dense discriminative classifier of $p(class|pixel feature)$ using the pseudo-labels from the target domain. While many methods focus on mitigating the issue of noisy pseudo-labels, they often overlook the underlying data distribution p(pixel feature|class) in both the source and target domains. To address this limitation, we propose the multi-prototype Gaussian-Mixture-based (ProtoGMM) model, which incorporates the GMM into contrastive losses to perform guided contrastive learning. Contrastive losses are commonly executed in the literature using memory banks, which can lead to class biases due to underrepresented classes. Furthermore, memory banks often have fixed capacities, potentially restricting the model's ability to capture diverse representations of the target/source domains. An alternative approach is to use global class prototypes (i.e. averaged features per category). However, the global prototypes are based on the unimodal distribution assumption per class, disregarding within-class variation. To address these challenges, we propose the ProtoGMM model. This novel approach involves estimating the underlying multi-prototype source distribution by utilizing the GMM on the feature space of the source samples. The components of the GMM model act as representative prototypes. To achieve increased intra-class semantic similarity, decreased inter-class similarity, and domain alignment between the source and target domains, we employ multi-prototype contrastive learning between source distribution and target samples. The experiments show the effectiveness of our method on UDA benchmarks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts
FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
토론
이 논문과 연결된 포럼 글이 아직 없습니다.