Related papers: Meta ControlNet: Enhancing Task Adaptation via Met…
We propose an end-to-end trainable Convolutional Neural Network (CNN), named GridDehazeNet, for single image dehazing. The GridDehazeNet consists of three modules: pre-processing, backbone, and post-processing. The trainable pre-processing…
The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard…
Self-supervised pre-training of transformer models has revolutionized NLP applications. Such pre-training with language modeling objectives provides a useful initial point for parameters that generalize well to new tasks with fine-tuning.…
Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…
Large Multimodal Models (LMMs) often rely on in-context learning (ICL) to perform new visual question answering (VQA) tasks with minimal supervision. However, ICL performance, especially in smaller LMMs, does not always improve…
Meta-learning has been proved to be an effective framework to address few-shot learning problems. The key challenge is how to minimize the generalization error of base learner across tasks. In this paper, we explore the concept hierarchy…
Transfer learning refers to the transfer of knowledge or information from a relevant source task to a target task. However, most existing works assume both tasks are sampled from a stationary task distribution, thereby leading to the…
Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…
Recent advances in deep learning, in particular enabled by hardware advances and big data, have provided impressive results across a wide range of computational problems such as computer vision, natural language, or reinforcement learning.…
The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A…
Diffusion-based Image Editing has achieved significant success in recent years. However, it remains challenging to achieve high-quality image editing while maintaining the background similarity without sacrificing speed or memory…
The requirements for real-world manipulation tasks are diverse and often conflicting; some tasks require precise motion while others require force compliance; some tasks require avoidance of certain regions, while others require convergence…
Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered that the slow convergence is partly due to conflicting…
Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…
With the advancement of diffusion models, there is a growing demand for high-quality, controllable image generation, particularly through methods that utilize one or multiple control signals based on ControlNet. However, in current…
Few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which…
Denoising diffusion probabilistic models have brought tremendous advances in generative tasks, achieving state-of-the-art performance thus far. Current diffusion model-based applications exploit the power of learned visual representations…
Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this…
Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works…
The high cost of acquiring and annotating samples has made the `few-shot' learning problem of prime importance. Existing works mainly focus on improving performance on clean data and overlook robustness concerns on the data perturbed with…