The Lottery Ticket Hypothesis (LTH) posits the existence of a sparse subnetwork (a.k.a. winning ticket) that can generalize comparably to its over-parameterized counterpart when trained from scratch. The common approach to finding a winning ticket is to preserve the original strong generalization through Iterative Pruning (IP) and transfer information useful for achieving the learned generalization by applying the resulting sparse mask to an untrained network. However, existing IP methods still struggle to generalize their observations beyond ad-hoc initialization and small-scale architectures or datasets, or they bypass these challenges by applying their mask to trained weights instead of initialized ones. In this paper, we demonstrate that the parameter sign configuration plays a crucial role in conveying useful information for generalization to any randomly initialized network. Through linear mode connectivity analysis, we observe that a sparse network trained by an existing IP method can retain its basin of attraction if its parameter signs and normalization layer parameters are preserved. To take a step closer to finding a winning ticket, we alleviate the reliance on normalization layer parameters by preventing high error barriers along the linear path between the sparse network trained by our method and its counterpart with initialized normalization layer parameters. Interestingly, across various architectures and datasets, we observe that any randomly initialized network can be optimized to exhibit low error barriers along the linear path to the sparse network trained by our method by inheriting its sparsity and parameter sign information, potentially achieving performance comparable to the original. The code is available at https://github.com/JungHunOh/AWS_ICLR2025.git.

Without access to the original training data, data-free quantization (DFQ) aims to recover the performance loss induced by quantization. Most previous works have focused on using an original network to extract the train data information, which is instilled into surrogate synthesized images. However, existing DFQ methods do not take into account important aspects of quantization: the extent of a computational-cost-and-accuracy trade-off varies for each image, depending on its task difficulty. To handle such varying trade-offs, several efforts have been made to dynamically allocate bit-widths for each image. Such dynamic quantization, however, remains challenging and unexplored in the data-free domain, because synthesized images of previous works fail to possess properties in natural test images that are crucial for learning the appropriate dynamic allocation policy: difficulty, its diversity, and its plausibility. By contrast, we propose a data-free quantization framework that is dynamic-friendly, by modeling varying extents of task difficulties with plausibility. We generate plausibly difficult images with soft labels, whose probabilities are allocated to a group of similar classes. Images with diverse and plausible difficulties enable us to train the framework to dynamically handle the varying trade-offs. Consequently, our framework achieves better accuracy-complexity Pareto front than existing data-free quantization approaches.

In real-world scenarios, image recognition tasks, such as semantic segmentation and object detection, often pose greater challenges due to the lack of information available within low-resolution (LR) content. Image super-resolution (SR) is one of the promising solutions for addressing the challenges. However, due to the ill-posed property of SR, it is challenging for typical SR methods to restore task-relevant high-frequency contents, which may dilute the advantage of utilizing the SR method. Therefore, in this paper, we propose Super-Resolution for Image Recognition (SR4IR) that effectively guides the generation of SR images beneficial to achieving satisfactory image recognition performance when processing LR images. The critical component of our SR4IR is the task-driven perceptual (TDP) loss that enables the SR network to acquire task-specific knowledge from a network tailored for a specific task. Moreover, we propose a cross-quality patch mix and an alternate training framework that significantly enhances the efficacy of the TDP loss by addressing potential problems when employing the TDP loss. Through extensive experiments, we demonstrate that our SR4IR achieves outstanding task performance by generating SR images useful for a specific image recognition task, including semantic segmentation, object detection, and image classification. The implementation code is available at https://github.com/JaehaKim97ISR4IR.

Image restoration tasks have witnessed great performance improvement in recent years by developing large deep models. Despite the outstanding performance, the heavy computation demanded by the deep models has restricted the application of image restoration. To lift the restriction, it is required to reduce the size of the networks while maintaining accuracy. Recently, N:M structured pruning has appeared as one of the effective and practical pruning approaches for making the model efficient with the accuracy constraint. However, it fails to account for different computational complexities and performance requirements for different layers of an image restoration network. To further optimize the trade-off between the efficiency and the restoration accuracy, we propose a novel pruning method that determines the pruning ratio for N:M structured sparsity at each layer. Extensive experimental results on super-resolution and deblurring tasks demonstrate the efficacy of our method which outperforms previous pruning methods significantly. PyTorch implementation for the proposed methods will be publicly available at https://github.com/JungHunOh/SLS_CVPR2022

Since the resurgence of deep neural networks (DNNs), image super-resolution (SR) has recently seen a huge progress in improving the quality of low resolution images, however at the great cost of computations and resources. Recently, there has been several efforts to make DNNs more efficient via quantization. However, SR demands pixel-level accuracy in the system, it is more difficult to perform quantization without significantly sacrificing SR performance. To this end, we introduce a new ultra-low precision yet effective quantization approach specifically designed for SR. In particular, we observe that in recent SR networks, each channel has different distribution characteristics. Thus we propose a channel-wise distribution-aware quantization scheme. Experimental results demonstrate that our proposed quantization, dubbed Distribution-Aware Quantization (DAQ), manages to greatly reduce the computational and resource costs without the significant sacrifice in SR performance, compared to other quantization methods.

The goal of filter pruning is to search for unimportant filters to remove in order to make convolutional neural networks (CNNs) efficient without sacrificing the performance in the process. The challenge lies in finding information that can help determine how important or relevant each filter is with respect to the final output of neural networks. In this work, we share our observation that the batch normalization (BN) parameters of pre-trained CNNs can be used to estimate the feature distribution of activation outputs, without processing of training data. Upon observation, we propose a simple yet effective filter pruning method by evaluating the importance of each filter based on the BN parameters of pre-trained CNNs. The experimental results on CIFAR-10 and ImageNet demonstrate that the proposed method can achieve outstanding performance with and without fine-tuning in terms of the trade-off between the accuracy drop and the reduction in computational complexity and number of parameters of pruned networks.