451 citations · 1.1k across the 28 of their papers we have counts for
29 papers
Is Large-Scale Pretraining the Secret to Good Domain Generalization?
Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis +2
Multi-Source Domain Generalization (DG) is the task of training on multiple source domains and achieving high classification performance on unseen target domains. Recent methods co…
Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction
Kuniaki Saito, Kihyuk Sohn, Chen-Yu Lee +1
Large language models require updates to remain up-to-date or adapt to new domains by fine-tuning them with new documents. One key is memorizing the latest information in a way tha…
ERM++: An Improved Baseline for Domain Generalization
Piotr Teterwak, Kuniaki Saito, Theodoros Tsiligkaridis +2
Domain Generalization (DG) aims to develop classifiers that can generalize to new, unseen data distributions, a critical capability when collecting new domain-specific data is impr…
Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection
Kuniaki Saito, Donghyun Kim, Piotr Teterwak +2
Building object detectors that are robust to domain shifts is critical for real-world applications. Prior approaches fine-tune a pre-trained backbone and risk overfitting it to in-…
Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval
Kuniaki Saito, Kihyuk Sohn, Xiang Zhang +4
In Composed Image Retrieval (CIR), a user combines a query image with text to describe their intended target. Existing methods rely on supervised learning of CIR models using label…
Prefix Conditioning Unifies Language and Label Supervision
Kuniaki Saito, Kihyuk Sohn, Xiang Zhang +4
Image-classification datasets have been used to pretrain image recognition models. Recently, web-scale image-caption datasets have emerged as a source of powerful pretraining alter…
Learning to Detect Every Thing in an Open World
Kuniaki Saito, Ping Hu, Trevor Darrell +1
Many open-world applications require the detection of novel objects, yet state-of-the-art object detection and instance segmentation networks do not excel at this task. The key iss…
Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density
Kuniaki Saito, Donghyun Kim, Piotr Teterwak +3
Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achievin…
VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
Dina Bashkirova, Dan Hendrycks, Donghyun Kim +5
Progress in machine learning is typically measured by training and testing a model on the same distribution of data, i.e., the same domain. This over-estimates future accuracy on o…
OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers
Kuniaki Saito, Donghyun Kim, Kate Saenko
Semi-supervised learning (SSL) is an effective means to leverage unlabeled data to improve a model's performance. Typical SSL methods like FixMatch assume that labeled and unlabele…
OVANet: One-vs-All Network for Universal Domain Adaptation
Kuniaki Saito, Kate Saenko
Universal Domain Adaptation (UNDA) aims to handle both domain-shift and category-shift between two datasets, where the main challenge is to transfer knowledge while rejecting unkno…
Self-supervised Visual Attribute Learning for Fashion Compatibility
Donghyun Kim, Kuniaki Saito, Samarth Mishra +3
Many self-supervised learning (SSL) methods have been successful in learning semantically meaningful visual representations by solving pretext tasks. However, prior work in SSL foc…
COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder
Kuniaki Saito, Kate Saenko, Ming-Yu Liu
Unsupervised image-to-image translation intends to learn a mapping of an image in a given domain to an analogous image in a different domain, without explicit supervision of the ma…
Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels
Donghyun Kim, Kuniaki Saito, Tae-Hyun Oh +3
Existing unsupervised domain adaptation methods aim to transfer knowledge from a label-rich source domain to an unlabeled target domain. However, obtaining labels for some source d…
Universal Domain Adaptation through Self Supervision
Kuniaki Saito, Donghyun Kim, Stan Sclaroff +1
Unsupervised domain adaptation methods traditionally assume that all source categories are present in the target domain. In practice, little may be known about the category overlap…
MULE: Multimodal Universal Language Embedding
Donghyun Kim, Kuniaki Saito, Kate Saenko +2
Existing vision-language methods typically support two languages at a time at most. In this paper, we present a modular approach which can easily be incorporated into existing visi…
Semi-supervised Domain Adaptation via Minimax Entropy
Kuniaki Saito, Donghyun Kim, Stan Sclaroff +2
Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision. However, we show that these…
TWINs: Two Weighted Inconsistency-reduced Networks for Partial Domain Adaptation
Toshihiko Matsuura, Kuniaki Saito, Tatsuya Harada
The task of unsupervised domain adaptation is proposed to transfer the knowledge of a label-rich domain (source domain) to a label-scarce domain (target domain). Matching feature d…
Multichannel Semantic Segmentation with Unsupervised Domain Adaptation
Kohei Watanabe, Kuniaki Saito, Yoshitaka Ushiku +1
Most contemporary robots have depth sensors, and research on semantic segmentation with RGBD images has shown that depth images boost the accuracy of segmentation. Since it is time…
Strong-Weak Distribution Alignment for Adaptive Object Detection
Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada +1
We propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detecti…
Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
Xingchao Peng, Ben Usman, Kuniaki Saito +3
Unsupervised transfer of object recognition models from synthetic to real data is an important problem with many potential applications. The challenge is how to "adapt" a model tra…
Open Set Domain Adaptation by Backpropagation
Kuniaki Saito, Shohei Yamamoto, Yoshitaka Ushiku +1
Numerous algorithms have been proposed for transferring knowledge from a label-rich domain (source) to a label-scarce domain (target). Almost all of them are proposed for a closed-…
Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
Kuniaki Saito, Kohei Watanabe, Yoshitaka Ushiku +1
In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a sou…
Adversarial Dropout Regularization
Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada +1
We present a method for transferring neural representations from label-rich source domains to unlabeled target domains. Recent adversarial methods proposed for this task learn to a…