Related papers: RealEra: Semantic-level Concept Erasure via Neighb…
Personalized text-to-image generation aims to synthesize novel images of a specific subject or style using only a few reference images. Recent methods based on Low-Rank Adaptation (LoRA) enable efficient single-concept customization by…
Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…
How can we effectively unlearn selected concepts from pre-trained generative foundation models without resorting to extensive retraining? This research introduces `continual unlearning', a novel paradigm that enables the targeted removal of…
Referring Expression Comprehension (REC) aims to localize specified entities or regions in an image based on natural language descriptions. While existing methods handle single-entity localization, they often ignore complex inter-entity…
While researches on model-based blind single image super-resolution (SISR) have achieved tremendous successes recently, most of them do not consider the image degradation sufficiently. Firstly, they always assume image noise obeys an…
Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes textual queries cannot accurately and comprehensively reflect…
Video object removal aims to eliminate target objects from videos while plausibly completing missing regions and preserving spatio-temporal consistency. Although diffusion models have recently advanced this task, it remains challenging to…
In vision-and-language grounding problems, fine-grained representations of the image are considered to be of paramount importance. Most of the current systems incorporate visual features and textual concepts as a sketch of an image.…
Pre-trained language models have achieved remarkable success across diverse applications but remain susceptible to spurious, concept-driven correlations that impair robustness and fairness. In this work, we introduce CURE, a novel and…
Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Removing such concepts is non-trivial because of a complex relationship between the concept, text…
Due to the significant information loss in low-resolution (LR) images, it has become extremely challenging to further advance the state-of-the-art of single image super-resolution (SISR). Reference-based super-resolution (RefSR), on the…
Recent advancements in image generation models have enabled personalized image creation with both user-defined subjects (content) and styles. Prior works achieved personalization by merging corresponding low-rank adapters (LoRAs) through…
Existing text-to-image generative models reflect or even amplify societal biases ingrained in their training data. This is especially concerning for human image generation where models are biased against certain demographic groups. Existing…
Generative multimodal models can exhibit safety failures that are inherently relational: two benign concepts can become unsafe when linked by a specific action or relation (e.g., child-drinking-wine). Existing unlearning and concept-erasure…
The remarkable ability of diffusion models to generate high-fidelity images has led to their widespread adoption. However, concerns have also arisen regarding their potential to produce Not Safe for Work (NSFW) content and exhibit social…
Referring object detection and referring image segmentation are important tasks that require joint understanding of visual information and natural language. Yet there has been evidence that current benchmark datasets suffer from bias, and…
Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…
Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…
Distributed representations provide a vector space that captures meaningful relationships between data instances. The distributed nature of these representations, however, entangles together multiple attributes or concepts of data instances…
Image super-resolution (SR) with generative adversarial networks (GAN) has achieved great success in restoring realistic details. However, it is notorious that GAN-based SR models will inevitably produce unpleasant and undesirable…