Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation

2023-01-01 · CVPR 2023 1 · Dong Zhao, Shuang Wang, Qi Zang, Dou Quan, Xiutiao Ye, Licheng Jiao

Unsupervised domain adaptation (UDA) in semantic segmentation transfers the knowledge of the source domain to the target one to improve the adaptability of the segmentation model in the target domain. The need to access labeled source data makes UDA unable to handle adaptation scenarios involving privacy, property rights protection, and confidentiality. In this paper, we focus on unsupervised model adaptation (UMA), also called source-free domain adaptation, which adapts a source-trained model to the target domain without accessing source data. We find that the online self-training method has the potential to be deployed in UMA, but the lack of source domain loss will greatly weaken the stability and adaptability of the method. We analyze the two possible reasons for the degradation of online self-training, i.e. inopportune updates of the teacher model and biased knowledge from source-trained model. Based on this, we propose a dynamic teacher update mechanism and a training-consistency based resampling strategy to improve the stability and adaptability of online self training. On multiple model adaptation benchmarks, our method obtains new state-of-the-art performance, which is comparable or even better than state-of-the-art UDA methods.

📄 PDF Abstract BibTeX

Code (1)

dzhaoxd/dt-st 공식 구현 pytorch

Tasks

Domain Adaptation Semantic Segmentation Source-Free Domain Adaptation Unsupervised Domain Adaptation

From Shallow Humor to Metaphor: Towards Label-Free Harmful Meme Detection via LMM Agent Self-Improvement

2025-12-25 · Jian Lang, Rongpei Hong, Ting Zhong, Leiting Chen 외 arxiv

The proliferation of harmful memes on online media poses significant risks to public health and stability. Existing detection methods heavily rely on large-scale labeled data for training, which necessitates substantial …

A Bag of Tricks for Few-Shot Class-Incremental Learning

2024-03-21 · Shuvendu Roy, Chunjong Park, Aldi Fahrezi, Ali Etemad

We present a bag of tricks framework for few-shot class-incremental learning (FSCIL), which is a challenging form of continual learning that involves continuous adaptation to new tasks with limited samples. FSCIL require…

class-incremental learning Class Incremental Learning Continual Learning Few-Shot Class-Incremental Learning+1

The Self-Learning Agent with a Progressive Neural Network Integrated Transformer

2025-04-03 · Ajay Sivakumar, Shalini, Vasantha Raj, Sebastian Sylvester

This paper introduces a self-learning agent that integrates LLaMA 3.2 with a Progressive Neural Network (PNN) for continual learning in conversational AI and code generation. The framework dynamically collects data, fine…

Code Generation Continual Learning Meta-Learning Self-Learning

Certainty robustness: Evaluating LLM stability under self-challenging prompts

2026-02-10 · Mohammadreza Saadat, Steve Nemzer arxiv

Large language models (LLMs) often present answers with high apparent confidence despite lacking an explicit mechanism for reasoning about certainty or truth. While existing benchmarks primarily evaluate single-turn accu…

Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning

2024-03-27 · CVPR 2025 1 · Huiyi Wang, Haodong Lu, Lina Yao, Dong Gong

Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on …

Continual Learning