PyTorchKR Papers

최신 논문

총 3,892편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2409.04482

SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields

This paper introduces a novel continual learning framework for synthesising novel views of multiple scenes, learning multiple 3D scenes incrementally, and updating the network parameters only with the training data of the upcoming new scene. We build on Neural Radiance Fields (NeRF), which uses multi-layer perceptron to model the density and radiance field of a scene as the implicit function. While NeRF and its extensions have shown a powerful capability of rendering photo-realistic novel views in a single 3D scene, managing these growing 3D NeRF assets efficiently is a new scientific problem. Very few works focus on the efficient representation or continuous learning capability of multiple scenes, which is crucial for the practical applications of NeRF. To achieve these goals, our key idea is to represent multiple scenes as the linear combination of a cross-scene weight matrix and a set of scene-specific weight matrices generated from a global parameter generator. Furthermore, we propose an uncertain surface knowledge distillation strategy to transfer the radiance field knowledge of previous scenes to the new model. Representing multiple 3D scenes with such weight matrices significantly reduces memory requirements. At the same time, the uncertain surface distillation strategy greatly overcomes the catastrophic forgetting problem and maintains the photo-realistic rendering quality of previous scenes. Experiments show that the proposed approach achieves state-of-the-art rendering quality of continual learning NeRF on NeRF-Synthetic, LLFF, and TanksAndTemples datasets while preserving extra low storage cost.

arXiv:2409.04778

LoCa: Logit Calibration for Knowledge Distillation

Knowledge Distillation (KD), aiming to train a better student model by mimicking the teacher model, plays an important role in model compression. One typical way is to align the output logits. However, we find a common issue named mis-instruction, that the student would be misled when the predictions based on teacher logits do not follow the labels. Meanwhile, there is other useful dark knowledge in the logits such as the class discriminability, which is vital for distillation. In this paper, we propose a simple yet effective Logit Calibration (LoCa) method, which calibrates the logits from the teacher model based on the ground-truth labels. The key insight is to correct the prediction (to address the mis-instruction issue) and maintain useful dark knowledge simultaneously. Our proposed LoCa does not require any additional parameters. Empirical results on image classification and text generation tasks demonstrate that LoCa can effectively improve the performance of baselines.

arXiv:2409.05359공식 코드 · Papers with Code

FedBrain-Distill: Communication-Efficient Federated Brain Tumor Classification Using Ensemble Knowledge Distillation on Non-IID Data

Brain is one the most complex organs in the human body. Due to its complexity, classification of brain tumors still poses a significant challenge, making brain tumors a particularly serious medical issue. Techniques such as Machine Learning (ML) coupled with Magnetic Resonance Imaging (MRI) have paved the way for doctors and medical institutions to classify different types of tumors. However, these techniques suffer from limitations that violate patients privacy. Federated Learning (FL) has recently been introduced to solve such an issue, but the FL itself suffers from limitations like communication costs and dependencies on model architecture, forcing all models to have identical architectures. In this paper, we propose FedBrain-Distill, an approach that leverages Knowledge Distillation (KD) in an FL setting that maintains the users privacy and ensures the independence of FL clients in terms of model architecture. FedBrain-Distill uses an ensemble of teachers that distill their knowledge to a simple student model. The evaluation of FedBrain-Distill demonstrated high-accuracy results for both Independent and Identically Distributed (IID) and non-IID data with substantial low communication costs on the real-world Figshare brain tumor dataset. It is worth mentioning that we used Dirichlet distribution to partition the data into IID and non-IID data. All the implementation details are accessible through our Github repository.

arXiv:2409.05564공식 코드 · Papers with Code

LEROjD: Lidar Extended Radar-Only Object Detection

Accurate 3D object detection is vital for automated driving. While lidar sensors are well suited for this task, they are expensive and have limitations in adverse weather conditions. 3+1D imaging radar sensors offer a cost-effective, robust alternative but face challenges due to their low resolution and high measurement noise. Existing 3+1D imaging radar datasets include radar and lidar data, enabling cross-modal model improvements. Although lidar should not be used during inference, it can aid the training of radar-only object detectors. We explore two strategies to transfer knowledge from the lidar to the radar domain and radar-only object detectors: 1. multi-stage training with sequential lidar point cloud thin-out, and 2. cross-modal knowledge distillation. In the multi-stage process, three thin-out methods are examined. Our results show significant performance gains of up to 4.2 percentage points in mean Average Precision with multi-stage training and up to 3.9 percentage points with knowledge distillation by initializing the student with the teacher's weights. The main benefit of these approaches is their applicability to other 3D object detection networks without altering their architecture, as we show by analyzing it on two different object detectors. Our code is available at https://github.com/rst-tu-dortmund/lerojd

arXiv:2409.05384

Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition

In spite of great success in many image recognition tasks achieved by recent deep models, directly applying them to recognize low-resolution images may suffer from low accuracy due to the missing of informative details during resolution degradation. However, these images are still recognizable for subjects who are familiar with the corresponding high-resolution ones. Inspired by that, we propose a teacher-student learning approach to facilitate low-resolution image recognition via hybrid order relational knowledge distillation. The approach refers to three streams: the teacher stream is pretrained to recognize high-resolution images in high accuracy, the student stream is learned to identify low-resolution images by mimicking the teacher's behaviors, and the extra assistant stream is introduced as bridge to help knowledge transfer across the teacher to the student. To extract sufficient knowledge for reducing the loss in accuracy, the learning of student is supervised with multiple losses, which preserves the similarities in various order relational structures. In this way, the capability of recovering missing details of familiar low-resolution images can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on metric learning, low-resolution image classification and low-resolution face recognition tasks show the effectiveness of our approach, while taking reduced models.

arXiv:2409.05620

Joint Input and Output Coordination for Class-Incremental Learning

Incremental learning is nontrivial due to severe catastrophic forgetting. Although storing a small amount of data on old tasks during incremental learning is a feasible solution, current strategies still do not 1) adequately address the class bias problem, and 2) alleviate the mutual interference between new and old tasks, and 3) consider the problem of class bias within tasks. This motivates us to propose a joint input and output coordination (JIOC) mechanism to address these issues. This mechanism assigns different weights to different categories of data according to the gradient of the output score, and uses knowledge distillation (KD) to reduce the mutual interference between the outputs of old and new tasks. The proposed mechanism is general and flexible, and can be incorporated into different incremental learning approaches that use memory storage. Extensive experiments show that our mechanism can significantly improve their performance.

arXiv:2409.03939

Experimentation in Content Moderation using RWKV

This paper investigates the RWKV model's efficacy in content moderation through targeted experimentation. We introduce a novel dataset specifically designed for distillation into smaller models, enhancing content moderation practices. This comprehensive dataset encompasses images, videos, sounds, and text data that present societal challenges. Leveraging advanced Large Language Models (LLMs), we generated an extensive set of responses -- 558,958 for text and 83,625 for images -- to train and refine content moderation systems. Our core experimentation involved fine-tuning the RWKV model, capitalizing on its CPU-efficient architecture to address large-scale content moderation tasks. By highlighting the dataset's potential for knowledge distillation, this study not only demonstrates RWKV's capability in improving the accuracy and efficiency of content moderation systems but also paves the way for developing more compact, resource-efficient models in this domain. Datasets and models can be found in HuggingFace: https://huggingface.co/modrwkv

arXiv:2409.03455

Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image Restoration

Multi-weather image restoration has witnessed incredible progress, while the increasing model capacity and expensive data acquisition impair its applications in memory-limited devices. Data-free distillation provides an alternative for allowing to learn a lightweight student model from a pre-trained teacher model without relying on the original training data. The existing data-free learning methods mainly optimize the models with the pseudo data generated by GANs or the real data collected from the Internet. However, they inevitably suffer from the problems of unstable training or domain shifts with the original data. In this paper, we propose a novel Data-free Distillation with Degradation-prompt Diffusion framework for multi-weather Image Restoration (D4IR). It replaces GANs with pre-trained diffusion models to avoid model collapse and incorporates a degradation-aware prompt adapter to facilitate content-driven conditional diffusion for generating domain-related images. Specifically, a contrast-based degradation prompt adapter is firstly designed to capture degradation-aware prompts from web-collected degraded images. Then, the collected unpaired clean images are perturbed to latent features of stable diffusion, and conditioned with the degradation-aware prompts to synthesize new domain-related degraded images for knowledge distillation. Experiments illustrate that our proposal achieves comparable performance to the model distilled with original training data, and is even superior to other mainstream unsupervised methods.

arXiv:2409.03550공식 코드 · Papers with Code

DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture

Diffusion models (DMs) have demonstrated exceptional generative capabilities across various areas, while they are hindered by slow inference speeds and high computational demands during deployment. The most common way to accelerate DMs involves reducing the number of denoising steps during generation, achieved through faster sampling solvers or knowledge distillation (KD). In contrast to prior approaches, we propose a novel method that transfers the capability of large pretrained DMs to faster architectures. Specifically, we employ KD in a distinct manner to compress DMs by distilling their generative ability into more rapid variants. Furthermore, considering that the source data is either unaccessible or too enormous to store for current generative models, we introduce a new paradigm for their distillation without source data, termed Data-Free Knowledge Distillation for Diffusion Models (DKDM). Generally, our established DKDM framework comprises two main components: 1) a DKDM objective that uses synthetic denoising data produced by pretrained DMs to optimize faster DMs without source data, and 2) a dynamic iterative distillation method that flexibly organizes the synthesis of denoising data, preventing it from slowing down the optimization process as the generation is slow. To our knowledge, this is the first attempt at using KD to distill DMs into any architecture in a data-free manner. Importantly, our DKDM is orthogonal to most existing acceleration methods, such as denoising step reduction, quantization and pruning. Experiments show that our DKDM is capable of deriving 2x faster DMs with performance remaining on par with the baseline. Notably, our DKDM enables pretrained DMs to function as "datasets" for training new DMs.

arXiv:2409.00880

Compressing VAE-Based Out-of-Distribution Detectors for Embedded Deployment

Out-of-distribution (OOD) detectors can act as safety monitors in embedded cyber-physical systems by identifying samples outside a machine learning model's training distribution to prevent potentially unsafe actions. However, OOD detectors are often implemented using deep neural networks, which makes it difficult to meet real-time deadlines on embedded systems with memory and power constraints. We consider the class of variational autoencoder (VAE) based OOD detectors where OOD detection is performed in latent space, and apply quantization, pruning, and knowledge distillation. These techniques have been explored for other deep models, but no work has considered their combined effect on latent space OOD detection. While these techniques increase the VAE's test loss, this does not correspond to a proportional decrease in OOD detection performance and we leverage this to develop lean OOD detectors capable of real-time inference on embedded CPUs and GPUs. We propose a design methodology that combines all three compression techniques and yields a significant decrease in memory and execution time while maintaining AUROC for a given OOD detector. We demonstrate this methodology with two existing OOD detectors on a Jetson Nano and reduce GPU and CPU inference time by 20% and 28% respectively while keeping AUROC within 5% of the baseline.

arXiv:2409.01990공식 코드 · Papers with Code

Designing Large Foundation Models for Efficient Training and Inference: A Survey

This paper focuses on modern efficient training and inference technologies on foundation models and illustrates them from two perspectives: model and system design. Model and System Design optimize LLM training and inference from different aspects to save computational resources, making LLMs more efficient, affordable, and more accessible. The paper list repository is available at https://github.com/NoakLiu/Efficient-Foundation-Models-Survey.

arXiv:2409.02020

Efficient Point Cloud Classification via Offline Distillation Framework and Negative-Weight Self-Distillation Technique

The rapid advancement in point cloud processing technologies has significantly increased the demand for efficient and compact models that achieve high-accuracy classification. Knowledge distillation has emerged as a potent model compression technique. However, traditional KD often requires extensive computational resources for forward inference of large teacher models, thereby reducing training efficiency for student models and increasing resource demands. To address these challenges, we introduce an innovative offline recording strategy that avoids the simultaneous loading of both teacher and student models, thereby reducing hardware demands. This approach feeds a multitude of augmented samples into the teacher model, recording both the data augmentation parameters and the corresponding logit outputs. By applying shape-level augmentation operations such as random scaling and translation, while excluding point-level operations like random jittering, the size of the records is significantly reduced. Additionally, to mitigate the issue of small student model over-imitating the teacher model's outputs and converging to suboptimal solutions, we incorporate a negative-weight self-distillation strategy. Experimental results demonstrate that the proposed distillation strategy enables the student model to achieve performance comparable to state-of-the-art models while maintaining lower parameter count. This approach strikes an optimal balance between performance and complexity. This study highlights the potential of our method to optimize knowledge distillation for point cloud classification tasks, particularly in resource-constrained environments, providing a novel solution for efficient point cloud analysis.

arXiv:2409.01212공식 코드 · Papers with Code

MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillation

With the rising demand for high-resolution (HR) images, No-Reference Image Quality Assessment (NR-IQA) gains more attention, as it can ecaluate image quality in real-time on mobile devices and enhance user experience. However, existing NR-IQA methods often resize or crop the HR images into small resolution, which leads to a loss of important details. And most of them are of high computational complexity, which hinders their application on mobile devices due to limited computational resources. To address these challenges, we propose MobileIQA, a novel approach that utilizes lightweight backbones to efficiently assess image quality while preserving image details through high-resolution input. MobileIQA employs the proposed multi-view attention learning (MAL) module to capture diverse opinions, simulating subjective opinions provided by different annotators during the dataset annotation process. The model uses a teacher model to guide the learning of a student model through knowledge distillation. This method significantly reduces computational complexity while maintaining high performance. Experiments demonstrate that MobileIQA outperforms novel IQA methods on evaluation metrics and computational efficiency. The code is available at https://github.com/chencn2020/MobileIQA.

arXiv:2409.02699

Collaborative Learning for Enhanced Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) endeavors to bridge the gap between a model trained on a labeled source domain and its deployment in an unlabeled target domain. However, current high-performance models demand significant resources, making deployment costs prohibitive and highlighting the need for compact, yet effective models. For UDA of lightweight models, Knowledge Distillation (KD) leveraging a Teacher-Student framework could be a common approach, but we found that domain shift in UDA leads to a significant increase in non-salient parameters in the teacher model, degrading model's generalization ability and transferring misleading information to the student model. Interestingly, we observed that this phenomenon occurs considerably less in the student model. Driven by this insight, we introduce Collaborative Learning for UDA (CLDA), a method that updates the teacher's non-salient parameters using the student model and at the same time utilizes the updated teacher model to improve UDA performance of the student model. Experiments show consistent performance improvements for both student and teacher models. For example, in semantic segmentation, CLDA achieves an improvement of +0.7% mIoU for the teacher model and +1.4% mIoU for the student model compared to the baseline model in the GTA-to-Cityscapes datasets. In the Synthia-to-Cityscapes dataset, it achieves an improvement of +0.8% mIoU and +2.0% mIoU for the teacher and student models, respectively.

arXiv:2409.02438

Non-target Divergence Hypothesis: Toward Understanding Domain Gaps in Cross-Modal Knowledge Distillation

Compared to single-modal knowledge distillation, cross-modal knowledge distillation faces more severe challenges due to domain gaps between modalities. Although various methods have proposed various solutions to overcome these challenges, there is still limited research on how domain gaps affect cross-modal knowledge distillation. This paper provides an in-depth analysis and evaluation of this issue. We first introduce the Non-Target Divergence Hypothesis (NTDH) to reveal the impact of domain gaps on cross-modal knowledge distillation. Our key finding is that domain gaps between modalities lead to distribution differences in non-target classes, and the smaller these differences, the better the performance of cross-modal knowledge distillation. Subsequently, based on Vapnik-Chervonenkis (VC) theory, we derive the upper and lower bounds of the approximation error for cross-modal knowledge distillation, thereby theoretically validating the NTDH. Finally, experiments on five cross-modal datasets further confirm the validity, generalisability, and applicability of the NTDH.

arXiv:2409.02049

Low-Resolution Face Recognition via Adaptable Instance-Relation Distillation

Low-resolution face recognition is a challenging task due to the missing of informative details. Recent approaches based on knowledge distillation have proven that high-resolution clues can well guide low-resolution face recognition via proper knowledge transfer. However, due to the distribution difference between training and testing faces, the learned models often suffer from poor adaptability. To address that, we split the knowledge transfer process into distillation and adaptation steps, and propose an adaptable instance-relation distillation approach to facilitate low-resolution face recognition. In the approach, the student distills knowledge from high-resolution teacher in both instance level and relation level, providing sufficient cross-resolution knowledge transfer. Then, the learned student can be adaptable to recognize low-resolution faces with adaptive batch normalization in inference. In this manner, the capability of recovering missing details of familiar low-resolution faces can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on low-resolution face recognition clearly demonstrate the effectiveness and adaptability of our approach.

arXiv:2409.01679

Adaptive Explicit Knowledge Transfer for Knowledge Distillation

Logit-based knowledge distillation (KD) for classification is cost-efficient compared to feature-based KD but often subject to inferior performance. Recently, it was shown that the performance of logit-based KD can be improved by effectively delivering the probability distribution for the non-target classes from the teacher model, which is known as `implicit (dark) knowledge', to the student model. Through gradient analysis, we first show that this actually has an effect of adaptively controlling the learning of implicit knowledge. Then, we propose a new loss that enables the student to learn explicit knowledge (i.e., the teacher's confidence about the target class) along with implicit knowledge in an adaptive manner. Furthermore, we propose to separate the classification and distillation tasks for effective distillation and inter-class relationship modeling. Experimental results demonstrate that the proposed method, called adaptive explicit knowledge transfer (AEKT) method, achieves improved performance compared to the state-of-the-art KD methods on the CIFAR-100 and ImageNet datasets.

arXiv:2409.01573

Improving Apple Object Detection with Occlusion-Enhanced Distillation

Apples growing in natural environments often face severe visual obstructions from leaves and branches. This significantly increases the risk of false detections in object detection tasks, thereby escalating the challenge. Addressing this issue, we introduce a technique called "Occlusion-Enhanced Distillation" (OED). This approach utilizes occlusion information to regularize the learning of semantically aligned features on occluded datasets and employs Exponential Moving Average (EMA) to enhance training stability. Specifically, we first design an occlusion-enhanced dataset that integrates Grounding DINO and SAM methods to extract occluding elements such as leaves and branches from each sample, creating occlusion examples that reflect the natural growth state of fruits. Additionally, we propose a multi-scale knowledge distillation strategy, where the student network uses images with increased occlusions as inputs, while the teacher network employs images without natural occlusions. Through this setup, the strategy guides the student network to learn from the teacher across scales of semantic and local features alignment, effectively narrowing the feature distance between occluded and non-occluded targets and enhancing the robustness of object detection. Lastly, to improve the stability of the student network, we introduce the EMA strategy, which aids the student network in learning more generalized feature expressions that are less affected by the noise of individual image occlusions. Our method significantly outperforms current state-of-the-art techniques through extensive comparative experiments.

arXiv:2409.02555

Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation

Recognizing objects in low-resolution images is a challenging task due to the lack of informative details. Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher model to a low-resolution student model by aligning cross-resolution representations. However, these approaches still face limitations in adapting to the situation where the recognized objects exhibit significant representation discrepancies between training and testing images. In this study, we propose a cross-resolution relational contrastive distillation approach to facilitate low-resolution object recognition. Our approach enables the student model to mimic the behavior of a well-trained teacher model which delivers high accuracy in identifying high-resolution objects. To extract sufficient knowledge, the student learning is supervised with contrastive relational distillation loss, which preserves the similarities in various relational structures in contrastive representation space. In this manner, the capability of recovering missing details of familiar low-resolution objects can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on low-resolution object classification and low-resolution face recognition clearly demonstrate the effectiveness and adaptability of our approach.

arXiv:2409.01128공식 코드 · Papers with Code

Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning

Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue that has been explored to some extent in Continual Learning (CL). However, due to privacy preservation requirements, some conventional methods, such as experience replay, are not directly applicable to FCCL. Existing FCCL methods mitigate forgetting by generating historical data through federated training of GANs or data-free knowledge distillation. However, these approaches often suffer from unstable training of generators or low-quality generated data, limiting their guidance for the model. To address this challenge, we propose a novel method of data replay based on diffusion models. Instead of training a diffusion model, we employ a pre-trained conditional diffusion model to reverse-engineer each class, searching the corresponding input conditions for each class within the model's input space, significantly reducing computational resources and time consumption while ensuring effective generation. Furthermore, we enhance the classifier's domain generalization ability on generated and real data through contrastive learning, indirectly improving the representational capability of generated data for real data. Comprehensive experiments demonstrate that our method significantly outperforms existing baselines. Code is available at https://github.com/jinglin-liang/DDDR.