Related papers: Doubly Abductive Counterfactual Inference for Text…
We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input…
Balancing fidelity and editability is essential in text-based image editing (TIE), where failures commonly lead to over- or under-editing issues. Existing methods typically rely on attention injections for structure preservation and…
Altering the content of an image with photo editing tools is a tedious task for an inexperienced user. Especially, when modifying the visual attributes of a specific object in an image without affecting other constituents such as background…
Text-to-image (T2I) diffusion models have demonstrated impressive performance in generating high-fidelity images, largely enabled by text-guided inference. However, this advantage often comes with a critical drawback: limited diversity, as…
Diffusion models have shown to be strong representation learners, showcasing state-of-the-art performance across multiple domains. Aside from accelerated sampling, DDIM also enables the inversion of real images back to their latent codes. A…
This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA),…
The recent success of text-to-image generation diffusion models has also revolutionized semantic image editing, enabling the manipulation of images based on query/target texts. Despite these advancements, a significant challenge lies in the…
Text-conditional image editing is a practical AIGC task that has recently emerged with great commercial and academic value. For real image editing, most diffusion model-based methods use DDIM Inversion as the first stage before editing.…
Text-based image editing, powered by generative diffusion models, lets users modify images through natural-language prompts and has dramatically simplified traditional workflows. Despite these advances, current methods still suffer from a…
Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively…
Text-to-image person re-identification (ReID) aims to retrieve images of a person based on a given textual description. The key challenge is to learn the relations between detailed information from visual and textual modalities. Existing…
Counterfactual generation lies at the core of various machine learning tasks, including image translation and controllable text generation. This generation process usually requires the identification of the disentangled latent…
In the field of Explainable AI (XAI), counterfactual (CF) explanations are one prominent method to interpret a black-box model by suggesting changes to the input that would alter a prediction. In real-world applications, the input is…
We present Causal-Adapter, a modular framework that adapts frozen text-to-image diffusion backbones for counterfactual image generation. Our method supports causal interventions on target attributes and consistently propagates their effects…
The widespread use of diffusion methods enables the creation of highly realistic images on demand, thereby posing significant risks to the integrity and safety of online information and highlighting the necessity of DeepFake detection. Our…
The problem of fair classification can be mollified if we develop a method to remove the embedded sensitive information from the classification features. This line of separating the sensitive information is developed through the causal…
Current methods of toxic language detection (TLD) typically rely on specific tokens to conduct decisions, which makes them suffer from lexical bias, leading to inferior performance and generalization. Lexical bias has both "useful" and…
Text-to-image (T2I) models can effectively capture the content or style of reference images to perform high-quality customization. A representative technique for this is fine-tuning using low-rank adaptations (LoRA), which enables efficient…
Diffusion Transformer (DiT) faces challenges when generating images with higher resolution compared at training resolution, causing especially structural degradation due to attention dilution. Previous approaches attempt to mitigate this by…
Counterfactuals are a popular framework for interpreting machine learning predictions. These what if explanations are notoriously challenging to create for computer vision models: standard gradient-based methods are prone to produce…