相关论文: Lightweight Diffusion Models with Distillation-Bas…

Neural Architecture Search (NAS), aiming at automatically designing network architectures by machines, is hoped and expected to bring about a new revolution in machine learning. Despite these high expectation, the effectiveness and…

Diffusion models (DMs) are powerful generative models capable of producing high-fidelity images but are constrained by high computational costs due to iterative multi-step inference. While Neural Architecture Search (NAS) can optimize DMs,…

Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method. During the search stage, DARTS trains a supernet by jointly optimizing architecture parameters and network parameters. During the…

Diffusion models are cutting-edge generative models adept at producing diverse, high-quality images. Despite their effectiveness, these models often require significant computational resources owing to their numerous sequential denoising…

Diffusion models have recently exhibited remarkable performance on synthetic data. After a diffusion path is selected, a base model, such as UNet, operates as a denoising autoencoder, primarily predicting noises that need to be eliminated…

This paper proposes a novel differentiable architecture search method by formulating it into a distribution learning problem. We treat the continuously relaxed architecture mixing weight as random variables, modeled by Dirichlet…

Neural Architecture Search (NAS) has gained widespread attention for its transformative potential in deep learning model design. However, the vast and complex search space of NAS leads to significant computational and time costs. Neural…

Neural Architecture Search (NAS) has demonstrated state-of-the-art performance on various computer vision tasks. Despite the superior performance achieved, the efficiency and generality of existing methods are highly valued due to their…

Large pretrained language models have achieved state-of-the-art results on a variety of downstream tasks. Knowledge Distillation (KD) into a smaller student model addresses their inefficiency, allowing for deployment in resource-constrained…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Neural architecture search automates the design of neural network architectures usually by exploring a large and thus complex architecture search space. To advance the architecture search, we present a graph diffusion-based NAS approach…

Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant architectures. To tackle such limitations of existing NAS methods, we propose a paradigm shift from NAS to a…

In recent years, neural architecture search (NAS) has received intensive scientific and industrial interest due to its capability of finding a neural architecture with high accuracy for various artificial intelligence tasks such as image…

Search space design is very critical to neural architecture search (NAS) algorithms. We propose a fine-grained search space comprised of atomic blocks, a minimal search unit that is much smaller than the ones used in recent NAS algorithms.…

Neural Architecture Search (NAS) has shown promising capability in learning text representation. However, existing text-based NAS neither performs a learnable fusion of neural operations to optimize the architecture, nor encodes the latent…

Distillation-aware Neural Architecture Search (DaNAS) aims to search for an optimal student architecture that obtains the best performance and/or efficiency when distilling the knowledge from a given teacher model. Previous DaNAS methods…

Standard Latent Diffusion Models rely on a complex, three-part architecture consisting of a separate encoder, decoder, and diffusion network, which are trained in multiple stages. This modular design is computationally inefficient, leads to…

End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability. Existing block-wise training methods offer means to alleviate this problem, but they rely on ad-hoc…

Neural architecture search (NAS) enables finding the best-performing architecture from a search space automatically. Most NAS methods exploit an over-parameterized network (i.e., a supernet) containing all possible architectures (i.e.,…

Image restoration aims to enhance low quality images, producing high quality images that exhibit natural visual characteristics and fine semantic attributes. Recently, the diffusion model has emerged as a powerful technique for image…