Related papers: ACE-LoRA: Adaptive Orthogonal Decoupling for Conti…

Continuous/Lifelong learning of high-dimensional data streams is a challenging research problem. In fact, fully retraining models each time new data become available is infeasible, due to computational and storage issues, while na\"ive…

Despite the great success of large-scale text-to-image diffusion models in image generation and image editing, existing methods still struggle to edit the layout of real images. Although a few works have been proposed to tackle this…

Human pose estimators are typically retrained from scratch or naively fine-tuned whenever keypoint sets, sensing modalities, or deployment domains change--an inefficient, compute-intensive practice that rarely matches field constraints. We…

Many approximate machine unlearning methods demonstrate strong logit-level forgetting -- such as near-zero accuracy on the forget set -- yet continue to preserve substantial information within their internal feature representations. We…

In recent years, image editing has garnered growing attention. However, general image editing models often fail to produce satisfactory results when confronted with new styles. The challenge lies in how to effectively fine-tune general…

This paper introduces a novel perspective to significantly mitigate catastrophic forgetting in continuous learning (CL), which emphasizes models' capacity to preserve existing knowledge and assimilate new information. Current replay-based…

In this work, we propose a new loss to improve feature discriminability and classification performance. Motivated by the adaptive cosine/coherence estimator (ACE), our proposed method incorporates angular information that is inherently…

Recent diffusion-based image editing methods commonly rely on text or high-level instructions to guide the generation process, offering intuitive but coarse control. In contrast, we focus on explicit, prompt-free editing, where the user…

Single image dehazing is a challenging ill-posed problem due to the severe information degeneration. However, existing deep learning based dehazing methods only adopt clear images as positive samples to guide the training of dehazing…

Large Language Models (LLMs) demonstrate exceptional performance across various tasks but demand substantial computational resources even for fine-tuning computation. Although Low-Rank Adaptation (LoRA) significantly alleviates memory…

In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On…

Processing visual data often involves small adjustments or sequences of changes, e.g., image filtering, surface smoothing, and animation. While established graphics techniques like normal mapping and video compression exploit redundancy to…

An image editing model should be able to perform diverse edits, ranging from object replacement, changing attributes or style, to performing actions or movement, which require many forms of reasoning. Current general instruction-guided…

In-context image generation and editing (ICGE) enables users to specify visual concepts through interleaved image-text prompts, demanding precise understanding and faithful execution of user intent. Although recent unified multimodal models…

Low-Rank Adaptation (LoRA) has emerged as a powerful and popular technique for personalization, enabling efficient adaptation of pre-trained image generation models for specific tasks without comprehensive retraining. While employing…

Diffusion models have significantly advanced image manipulation techniques, and their ability to generate photorealistic images is beginning to transform retail workflows, particularly in presale visualization. Beyond artistic style…

In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient specificity, and diverse interpretations of natural language,…

Continual Relation Extraction (CRE) aims to continually learn new emerging relations while avoiding catastrophic forgetting. Existing CRE methods mainly use memory replay and contrastive learning to mitigate catastrophic forgetting.…

Fine-tuning is the primary methodology for tailoring pre-trained large language models to specific tasks. As the model's scale and the diversity of tasks expand, parameter-efficient fine-tuning methods are of paramount importance. One of…

In many real-world scenarios, data to train machine learning models become available over time. However, neural network models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon…