PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion

Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and extensive data collection remains a bottleneck. On the other hand, the integration of existing diffusion models, each specialized for different controls and operating in unique latent spaces, poses a challenge due to incompatible image resolutions and latent space embedding structures, hindering their joint use. Addressing these constraints, we present "PanGu-Draw", a novel latent diffusion model designed for resource-efficient text-to-image synthesis that adeptly accommodates multiple control signals. We first propose a resource-efficient Time-Decoupling Training Strategy, which splits the monolithic text-to-image model into structure and texture generators. Each generator is trained using a regimen that maximizes data utilization and computational efficiency, cutting data preparation by 48% and reducing training resources by 51%. Secondly, we introduce "Coop-Diffusion", an algorithm that enables the cooperative use of various pre-trained diffusion models with different latent spaces and predefined resolutions within a unified denoising process. This allows for multi-control image synthesis at arbitrary resolutions without the necessity for additional data or retraining. Empirical validations of Pangu-Draw show its exceptional prowess in text-to-image and multi-control image generation, suggesting a promising direction for future model training efficiencies and generation versatility. The largest 5B T2I PanGu-Draw model is released on the Ascend platform. Project page: $\href{https://pangu-draw.github.io}{this~https~URL}$

Learning Low-Rank Representations for Model Compression

Vector Quantization (VQ) is an appealing model compression method to obtain a tiny model with less accuracy loss. While methods to obtain better codebooks and codes under fixed clustering dimensionality have been extensively studied, optimizations of the vectors in favour of clustering performance are not carefully considered, especially via the reduction of vector dimensionality. This paper reports our recent progress on the combination of dimensionality compression and vector quantization, proposing a Low-Rank Representation Vector Quantization ($\text{LR}^2\text{VQ}$) method that outperforms previous VQ algorithms in various tasks and architectures. $\text{LR}^2\text{VQ}$ joins low-rank representation with subvector clustering to construct a new kind of building block that is directly optimized through end-to-end training over the task loss. Our proposed design pattern introduces three hyper-parameters, the number of clusters $k$, the size of subvectors $m$ and the clustering dimensionality $\tilde{d}$. In our method, the compression ratio could be directly controlled by $m$, and the final accuracy is solely determined by $\tilde{d}$. We recognize $\tilde{d}$ as a trade-off between low-rank approximation error and clustering error and carry out both theoretical analysis and experimental observations that empower the estimation of the proper $\tilde{d}$ before fine-tunning. With a proper $\tilde{d}$, we evaluate $\text{LR}^2\text{VQ}$ with ResNet-18/ResNet-50 on ImageNet classification datasets, achieving 2.8\%/1.0\% top-1 accuracy improvements over the current state-of-the-art VQ-based compression algorithms with 43$\times$/31$\times$ compression factor.

EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones

The superior performance of modern deep networks usually comes at the price of a costly training procedure. In this paper, we present a novel curriculum learning approach for the efficient training of visual backbones (e.g., vision Transformers). The proposed method is inspired by the phenomenon that deep networks mainly learn to recognize some 'easier-to-learn' discriminative patterns within each example at earlier stages of training, e.g., the lower-frequency components of images and the original information before data augmentation. Driven by this observation, we propose a curriculum where the model always leverages all the training data at each epoch, while the curriculum starts with only exposing the 'easier-to-learn' patterns of each example, and introduces gradually more difficult patterns. To implement this idea, we 1) introduce a cropping operation in the Fourier spectrum of the inputs, which enables the model to learn from only the lower-frequency components efficiently, and 2) demonstrate that exposing the features of original images amounts to adopting weaker data augmentation. Our resulting algorithm, EfficientTrain, is simple, general, yet surprisingly effective. For example, it reduces the training time of a wide variety of popular models (e.g., ConvNeXts, DeiT, PVT, and Swin/CSWin Transformers) by more than ${1.5\times}$ on ImageNet-1K/22K without sacrificing the accuracy. It is effective for self-supervised learning (i.e., MAE) as well. Code is available at https://github.com/LeapLabTHU/EfficientTrain.

Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs

In this paper, we propose a Collaboration of Experts (CoE) framework to pool together the expertise of multiple networks towards a common aim. Each expert is an individual network with expertise on a unique portion of the dataset, which enhances the collective capacity. Given a sample, an expert is selected by the delegator, which simultaneously outputs a rough prediction to support early termination. To fulfill this framework, we propose three modules to impel each model to play its role, namely weight generation module (WGM), label generation module (LGM) and variance calculation module (VCM). Our method achieves the state-of-the-art performance on ImageNet, 80.7% top-1 accuracy with 194M FLOPs. Combined with PWLU activation function and CondConv, CoE further achieves the accuracy of 80.0% with only 100M FLOPs for the first time. More importantly, our method is hardware friendly and achieves a 3-6x speedup compared with some existing conditional computation approaches.

Learning specialized activation functions with the Piecewise Linear Unit

The choice of activation functions is crucial for modern deep neural networks. Popular hand-designed activation functions like Rectified Linear Unit(ReLU) and its variants show promising performance in various tasks and models. Swish, the automatically discovered activation function, has been proposed and outperforms ReLU on many challenging datasets. However, it has two main drawbacks. First, the tree-based search space is highly discrete and restricted, which is difficult for searching. Second, the sample-based searching method is inefficient, making it infeasible to find specialized activation functions for each dataset or neural architecture. To tackle these drawbacks, we propose a new activation function called Piecewise Linear Unit(PWLU), which incorporates a carefully designed formulation and learning method. It can learn specialized activation functions and achieves SOTA performance on large-scale datasets like ImageNet and COCO. For example, on ImageNet classification dataset, PWLU improves 0.9%/0.53%/1.0%/1.7%/1.0% top-1 accuracy over Swish for ResNet-18/ResNet-50/MobileNet-V2/MobileNet-V3/EfficientNet-B0. PWLU is also easy to implement and efficient at inference, which can be widely applied in real-world applications.

FixNorm: Dissecting Weight Decay for Training Deep Neural Networks

Weight decay is a widely used technique for training Deep Neural Networks(DNN). It greatly affects generalization performance but the underlying mechanisms are not fully understood. Recent works show that for layers followed by normalizations, weight decay mainly affects the effective learning rate. However, despite normalizations have been extensively adopted in modern DNNs, layers such as the final fully-connected layer do not satisfy this precondition. For these layers, the effects of weight decay are still unclear. In this paper, we comprehensively investigate the mechanisms of weight decay and find that except for influencing effective learning rate, weight decay has another distinct mechanism that is equally important: affecting generalization performance by controlling cross-boundary risk. These two mechanisms together give a more comprehensive explanation for the effects of weight decay. Based on this discovery, we propose a new training method called FixNorm, which discards weight decay and directly controls the two mechanisms. We also propose a simple yet effective method to tune hyperparameters of FixNorm, which can find near-optimal solutions in a few trials. On ImageNet classification task, training EfficientNet-B0 with FixNorm achieves 77.7%, which outperforms the original baseline by a clear margin. Surprisingly, when scaling MobileNetV2 to the same FLOPS and applying the same tricks with EfficientNet-B0, training with FixNorm achieves 77.4%, which is only 0.3% lower. A series of SOTA results show the importance of well-tuned training procedures, and further verify the effectiveness of our approach. We set up more well-tuned baselines using FixNorm, to facilitate fair comparisons in the community.

AutoBSS: An Efficient Algorithm for Block Stacking Style Search

Neural network architecture design mostly focuses on the new convolutional operator or special topological structure of network block, little attention is drawn to the configuration of stacking each block, called Block Stacking Style (BSS). Recent studies show that BSS may also have an unneglectable impact on networks, thus we design an efficient algorithm to search it automatically. The proposed method, AutoBSS, is a novel AutoML algorithm based on Bayesian optimization by iteratively refining and clustering Block Stacking Style Code (BSSC), which can find optimal BSS in a few trials without biased evaluation. On ImageNet classification task, ResNet50/MobileNetV2/EfficientNet-B0 with our searched BSS achieve 79.29%/74.5%/77.79%, which outperform the original baselines by a large margin. More importantly, experimental results on model compression, object detection and instance segmentation show the strong generalizability of the proposed AutoBSS, and further verify the unneglectable impact of BSS on neural networks.

DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks

Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compress models. Although some efficient network structures have been proposed, such as MobileNet or ShuffleNet, we find that there still exists redundant information between convolution kernels. To address this issue, we propose a novel dynamic convolution method to adaptively generate convolution kernels based on image contents. To demonstrate the effectiveness, we apply dynamic convolution on multiple state-of-the-art CNNs. On one hand, we can reduce the computation cost remarkably while maintaining the performance. For ShuffleNetV2/MobileNetV2/ResNet18/ResNet50, DyNet can reduce 37.0/54.7/67.2/71.3% FLOPs without loss of accuracy. On the other hand, the performance can be largely boosted if the computation cost is maintained. Based on the architecture MobileNetV3-Small/Large, DyNet achieves 70.3/77.1% Top-1 accuracy on ImageNet with an improvement of 2.9/1.9%. To verify the scalability, we also apply DyNet on segmentation task, the results show that DyNet can reduce 69.3% FLOPs while maintaining Mean IoU on segmentation task.

BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search

Automatic neural architecture search techniques are becoming increasingly important in machine learning area. Especially, weight sharing methods have shown remarkable potentials on searching good network architectures with few computational resources. However, existing weight sharing methods mainly suffer limitations on searching strategies: these methods either uniformly train all network paths to convergence which introduces conflicts between branches and wastes a large amount of computation on unpromising candidates, or selectively train branches with different frequency which leads to unfair evaluation and comparison among paths. To address these issues, we propose a novel neural architecture search method with balanced training strategy to ensure fair comparisons and a selective drop mechanism to reduce conflicts among candidate paths. The experimental results show that our proposed method can achieve a leading performance of 79.0% on ImageNet under mobile settings, which outperforms other state-of-the-art methods in both accuracy and efficiency.

Adversarial AutoAugment

Data augmentation (DA) has been widely utilized to improve generalization in training deep neural networks. Recently, human-designed data augmentation has been gradually replaced by automatically learned augmentation policy. Through finding the best policy in well-designed search space of data augmentation, AutoAugment can significantly improve validation accuracy on image classification tasks. However, this approach is not computationally practical for large-scale problems. In this paper, we develop an adversarial method to arrive at a computationally-affordable solution called Adversarial AutoAugment, which can simultaneously optimize target related object and augmentation policy search loss. The augmentation policy network attempts to increase the training loss of a target network through generating adversarial augmentation policies, while the target network can learn more robust features from harder examples to improve the generalization. In contrast to prior work, we reuse the computation in target network training for policy evaluation, and dispense with the retraining of the target network. Compared to AutoAugment, this leads to about 12x reduction in computing cost and 11x shortening in time overhead on ImageNet. We show experimental results of our approach on CIFAR-10/CIFAR-100, ImageNet, and demonstrate significant performance improvements over state-of-the-art. On CIFAR-10, we achieve a top-1 test error of 1.36%, which is the currently best performing single model. On ImageNet, we achieve a leading performance of top-1 accuracy 79.40% on ResNet-50 and 80.00% on ResNet-50-D without extra data.