# Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memory

arXiv: https://arxiv.org/abs/2308.13236 · HTML: https://mlsanity.com/paper/2308.13236/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 80 of its 113 references that are in the map.
- First posted on arXiv 25 Aug 2023.

## Builds on (most cited first, 30 of 80)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Domain Adaptive Faster R-CNN for Object Detection in the Wild](https://mlsanity.com/paper/1803.03243/) (2018)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Semantic Foggy Scene Understanding with Synthetic Data](https://mlsanity.com/paper/1708.07819/) (2017)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.14887/) (2021)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [Strong-Weak Distribution Alignment for Adaptive Object Detection](https://mlsanity.com/paper/1812.04798/) (2018)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)

## Built on by (most cited first, 11 of 11)

- [Historical Test-time Prompt Tuning for Vision Foundation Models](https://mlsanity.com/paper/2410.20346/) (2024)
- [MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders](https://mlsanity.com/paper/2405.07696/) (2024)
- [Language-Guided Instance-Aware Domain-Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2404.03799/) (2024)
- [Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation](https://mlsanity.com/paper/2312.06331/) (2023)
- [Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Tasks](https://mlsanity.com/paper/2407.01327/) (2024)
- [Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA](https://mlsanity.com/paper/2503.10225/) (2025)
- [Incremental Pseudo-Labeling for Black-Box Unsupervised Domain Adaptation](https://mlsanity.com/paper/2405.16437/) (2024)
- [Single Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentation](https://mlsanity.com/paper/2508.01661/) (2025)
- [Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation](https://mlsanity.com/paper/2509.00509/) (2025)
- [Black-Box Time-Series Domain Adaptation via Cross-Prompt Foundation Models](https://mlsanity.com/paper/2510.00487/) (2025)
- [Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation](https://mlsanity.com/paper/2603.22908/) (2026)

## Abstract (arXiv)

Black-box unsupervised domain adaptation (UDA) learns with source predictions of target data without accessing either source data or source models during training, and it has clear superiority in data privacy and flexibility in target network selection. However, the source predictions of target data are often noisy and training with them is prone to learning collapses. We propose BiMem, a bi-directional memorization mechanism that learns to remember useful and representative information to correct noisy pseudo labels on the fly, leading to robust black-box UDA that can generalize across different visual recognition tasks. BiMem constructs three types of memory, including sensory memory, short-term memory, and long-term memory, which interact in a bi-directional manner for comprehensive and robust memorization of learnt features. It includes a forward memorization flow that identifies and stores useful features and a backward calibration flow that rectifies features' pseudo labels progressively. Extensive experiments show that BiMem achieves superior domain adaptation performance consistently across various visual recognition tasks such as image classification, semantic segmentation and object detection.