Batch Weight for Domain Adaptation With Mass Shift

Bińkowski, Mikołaj; Hjelm, Devon; Courville, Aaron

doi:10.1109/iccv.2019.00193

Cited by 9 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another interesting direction is unsupervised domain transfer, where support alignment is more desired than existing distribution alignment methods due to mode imbalance (Binkowski et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

Adversarial Support Alignment

Tong¹,

Garipov²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

We study the problem of aligning the supports of distributions. Compared to the existing work on distribution alignment, support alignment does not require the densities to be matched. We propose symmetric support difference as a divergence measure to quantify the mismatch between supports. We show that select discriminators (e.g. discriminator trained for Jensen-Shannon divergence) are able to map support differences as support differences in their one-dimensional output space. Following this result, our method aligns supports by minimizing a symmetrized relaxed optimal transport cost in the discriminator 1D space via an adversarial process. Furthermore, we show that our approach can be viewed as a limit of existing notions of alignment by increasing transportation assignment tolerance. We quantitatively evaluate the method across domain adaptation tasks with shifts in label distributions. Our experiments 1 show that the proposed method is more robust against these shifts than other alignment-based baselines.

show abstract

Section: Discussionmentioning

confidence: 99%

Adversarial Support Alignment

Tong¹,

Garipov²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A work closely related to ours [4] explicitly introduces a weighting network to reweight batches during a GAN training. However, their framework, in line with cycle-GAN, differs from ours as they focus on the divergence given by a domain discriminator (H-divergence) instead of the Y-discrepancy.…”

Section: B Adversarial Domain Adaptation Under Target Shiftmentioning

confidence: 99%

Adversarial Weighting for Domain Adaptation in Regression

Mathelin

Richard

Mougeot

et al. 2021

2021 IEEE 33rd International Conference on Tools With Artificial Intelligence (ICTAI)

View full text Add to dashboard Cite

We present a novel instance-based approach to handle regression tasks in the context of supervised domain adaptation under an assumption of covariate shift. The approach developed in this paper is based on the assumption that the task on the target domain can be efficiently learned by adequately reweighting the source instances during training phase. We introduce a novel formulation of the optimization objective for domain adaptation which relies on a discrepancy distance characterizing the difference between domains according to a specific task and a class of hypotheses. To solve this problem, we develop an adversarial network algorithm which learns both the source weighting scheme and the task in one feed-forward gradient descent. We provide numerical evidence of the relevance of the method on public data sets for regression domain adaptation through reproducible experiments.

show abstract

“…Another way to bridge the domain gap is to define a specific domain shift metric that is then minimized during training [51,52,28,12,82,58,29,62,33,95,39,34,93,94,36,59]. Other widely used approaches include generating realistic-looking synthetic images [69,20,2,98,97], incorporating self-training [70,6,18,75], transferring model weights between different domains [63,64], and using domain-specific batch normalization [5]. The method of [79] introduces a self-supervised auxiliary task such as detecting image-rotation in unlabeled target domain images for cross-domain image classification and served as an inspiration to us.…”

Section: Related Workmentioning

confidence: 99%

Leveraging Self-Supervision for Cross-Domain Crowd Counting

Liu¹,

Durasov²,

Fua³

2021

Preprint

View full text Add to dashboard Cite

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. While effective, these data-driven approaches rely on large amount of data annotation to achieve good performance, which stops these models from being deployed in emergencies during which data annotation is either too costly or cannot be obtained fast enough.One popular solution is to use synthetic data for training. Unfortunately, due to domain shift, the resulting models generalize poorly on real imagery. We remedy this shortcoming by training with both synthetic images, along with their associated labels, and unlabeled real images. To this end, we force our network to learn perspective-aware features by training it to recognize upside-down real images from regular ones and incorporate into it the ability to predict its own uncertainty so that it can generate useful pseudo labels for fine-tuning purposes. This yields an algorithm that consistently outperforms state-of-the-art cross-domain crowd counting ones without any extra computation at inference time.

show abstract

Batch Weight for Domain Adaptation With Mass Shift

Cited by 9 publications

References 18 publications

Adversarial Support Alignment

Adversarial Support Alignment

Adversarial Weighting for Domain Adaptation in Regression

Leveraging Self-Supervision for Cross-Domain Crowd Counting

Contact Info

Product

Resources

About