Recent advancements in text-guided image editing have achieved notable success by leveraging natural language prompts for fine-grained semantic control. However, certain editing semantics are challenging to specify precisely using textual descriptions alone. A practical alternative involves learning editing semantics from paired source-target examples. Existing exemplar-based editing methods still rely on text prompts describing the change within paired examples or learning implicit text-based editing instructions. In this paper, we introduce PairEdit, a novel visual editing method designed to effectively learn complex editing semantics from a limited number of image pairs or even a single image pair, without using any textual guidance. We propose a target noise prediction that explicitly models semantic variations within paired images through a guidance direction term. Moreover, we introduce a content-preserving noise schedule to facilitate more effective semantic learning. We also propose optimizing distinct LoRAs to disentangle the learning of semantic variations from content. Extensive qualitative and quantitative evaluations demonstrate that PairEdit successfully learns intricate semantics while significantly improving content consistency compared to baseline methods. Code is available at https://github.com/xudonmao/PairEdit.

Ensemble learning improves the capability of convolutional neural network (CNN)-based discriminators, whose performance is crucial to the quality of generated samples in generative adversarial network (GAN). However, this learning strategy results in a significant increase in the number of parameters along with computational overhead. Meanwhile, the suitable number of discriminators required to enhance GAN performance is still being investigated. To mitigate these issues, we propose an evidential discriminator for GAN (EviD-GAN)-code is available at https://github.com/Tohokantche/EviD-GAN-to learn both the model (epistemic) and data (aleatoric) uncertainties. Specifically, by analyzing three GAN models, the relation between the distribution of discriminator's output and the generator performance has been discovered yielding a general formulation of GAN framework. With the above analysis, the evidential discriminator learns the degree of aleatoric and epistemic uncertainties via imposing a higher order distribution constraint over the likelihood as expressed in the discriminator's output. This constraint can learn an ensemble of likelihood functions corresponding to an infinite set of discriminators. Thus, EviD-GAN aggregates knowledge through the ensemble learning of discriminator that allows the generator to benefit from an informative gradient flow at a negligible computational cost. Furthermore, inspired by the gradient direction in maximum mean discrepancy (MMD)-repulsive GAN, we design an asymmetric regularization scheme for EviD-GAN. Unlike MMD-repulsive GAN that performs at the distribution level, our regularization scheme is based on a pairwise loss function, performs at the sample level, and is characterized by an asymmetric behavior during the training of generator and discriminator. Experimental results show that the proposed evidential discriminator is cost-effective, consistently improves GAN in terms of Frechet inception distance (FID) and inception score (IS), and performs better than other competing models that use multiple discriminators.

GAN inversion aims to invert an input image into the latent space of a pre-trained GAN. Despite the recent advances in GAN inversion, there remain challenges to mitigate the tradeoff between distortion and editability, i.e. reconstructing the input image accurately and editing the inverted image with a small visual quality drop. The recently proposed pivotal tuning model makes significant progress towards reconstruction and editability, by using a two-step approach that first inverts the input image into a latent code, called pivot code, and then alters the generator so that the input image can be accurately mapped into the pivot code. Here, we show that both reconstruction and editability can be improved by a proper design of the pivot code. We present a simple yet effective method, named cycle encoding, for a high-quality pivot code. The key idea of our method is to progressively train an encoder in varying spaces according to a cycle scheme: W->W+->W. This training methodology preserves the properties of both W and W+ spaces, i.e. high editability of W and low distortion of W+. To further decrease the distortion, we also propose to refine the pivot code with an optimization-based method, where a regularization term is introduced to reduce the degradation in editability. Qualitative and quantitative comparisons to several state-of-the-art methods demonstrate the superiority of our approach.

One way of addressing the problem of unsupervised domain adaptation (UDA) is to perform adversarial training between two classifiers and their shared feature extractor. The two classifiers are enforced to detect the misaligned regions between the source and target domains, while the feature extractor aligns the features by confusing the classifiers. Although this method yields improvement, it ignores the relationship among target neighbors, which may consequently limit the model performance. In this work, we propose a new alignment strategy based on the "cluster assumption" to ensure the aligned target features preserve their clusters by avoiding overlap with decision boundaries. Furthermore, to make the aligned features more compact, we constrain them to be ro-bust against adversarial perturbation using the different views of the classifiers. Extensive experiments demonstrate the effectiveness of our solution on various datasets.

Recent approaches to unsupervised domain adaptation focus on transferring knowledge from source (labeled) data to target (unlabeled) data. Both data types share the same class space but originate from different domains. One way to achieve this transfer is tasking two classifiers to detect target features that diverge from source features. Meanwhile, a feature generator is adversarially refined to match the detected features with the source ones. However, the aligned features are still subject to ambiguity. Samples that are not smoothly distributed on the latent manifold are often missed in training. Moreover, target data may not be sufficient for adversarial learning. To overcome these problems, our proposed Adversarially Smoothed Feature Alignment (AdvSFA) model is designed to identify ambiguous target inputs by maximizing classifiers discrepancy in an extended class space. This enables the generator to receive valuable feedback from the classifiers and consequently learn more discriminative and smooth representation. Imposing smoothness on the latent manifold is a desirable property to improve model generalization and avoid having neighboring samples of different classes. To further promote such property, we not only task the generator to conduct feature alignment on target examples and but also in-between them. By adopting these constraints, our method shows a remarkable improvement across different adaptation tasks using two benchmark datasets.

We address the problem of unsupervised domain adaptation (UDA) which aims at adapting models trained on a labeled domain to a completely unlabeled domain. One way to achieve this goal is to learn a domain-invariant representation. However, this approach is subject to two challenges: samples from two domains are insufficient to guarantee domain-invariance at most part of the latent space, and neighboring samples from the target domain may not belong to the same class on the low-dimensional manifold. To mitigate these shortcomings, we propose two strategies. First, we incorporate a domain mixup strategy in domain adversarial learning model by linearly interpolating between the source and target domain samples. This allows the latent space to be continuous and yields an improvement of the domain matching. Second, the domain discriminator is regularized via judging the relative difference between both domains for the input mixup features, which speeds up the domain matching. Experiment results show that our proposed model achieves a superior performance on different tasks under various domain shifts and data complexity.