PyTorchKR Papers

최신 논문

총 1,512편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2312.04193공식 코드 · Papers with Code

Language Model Knowledge Distillation for Efficient Question Answering in Spanish

Recent advances in the development of pre-trained Spanish language models has led to significant progress in many Natural Language Processing (NLP) tasks, such as question answering. However, the lack of efficient models imposes a barrier for the adoption of such models in resource-constrained environments. Therefore, smaller distilled models for the Spanish language could be proven to be highly scalable and facilitate their further adoption on a variety of tasks and scenarios. In this work, we take one step in this direction by developing SpanishTinyRoBERTa, a compressed language model based on RoBERTa for efficient question answering in Spanish. To achieve this, we employ knowledge distillation from a large model onto a lighter model that allows for a wider implementation, even in areas with limited computational resources, whilst attaining negligible performance sacrifice. Our experiments show that the dense distilled model can still preserve the performance of its larger counterpart, while significantly increasing inference speedup. This work serves as a starting point for further research and investigation of model compression efforts for Spanish language models across various NLP tasks.

arXiv:2312.04066공식 코드 · Papers with Code

Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance

Unsupervised domain adaptation (UDA) tries to overcome the tedious work of labeling data by leveraging a labeled source dataset and transferring its knowledge to a similar but different target dataset. Meanwhile, current vision-language models exhibit remarkable zero-shot prediction capabilities. In this work, we combine knowledge gained through UDA with the inherent knowledge of vision-language models. We introduce a strong-weak guidance learning scheme that employs zero-shot predictions to help align the source and target dataset. For the strong guidance, we expand the source dataset with the most confident samples of the target dataset. Additionally, we employ a knowledge distillation loss as weak guidance. The strong guidance uses hard labels but is only applied to the most confident predictions from the target dataset. Conversely, the weak guidance is employed to the whole dataset but uses soft labels. The weak guidance is implemented as a knowledge distillation loss with (shifted) zero-shot predictions. We show that our method complements and benefits from prompt adaptation techniques for vision-language models. We conduct experiments and ablation studies on three benchmarks (OfficeHome, VisDA, and DomainNet), outperforming state-of-the-art methods. Our ablation studies further demonstrate the contributions of different components of our algorithm.

arXiv:2312.04168공식 코드 · Papers with Code

Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation

In recent years, knowledge distillation methods based on contrastive learning have achieved promising results on image classification and object detection tasks. However, in this line of research, we note that less attention is paid to semantic segmentation. Existing methods heavily rely on data augmentation and memory buffer, which entail high computational resource demands when applying them to handle semantic segmentation that requires to preserve high-resolution feature maps for making dense pixel-wise predictions. In order to address this problem, we present Augmentation-free Dense Contrastive Knowledge Distillation (Af-DCD), a new contrastive distillation learning paradigm to train compact and accurate deep neural networks for semantic segmentation applications. Af-DCD leverages a masked feature mimicking strategy, and formulates a novel contrastive learning loss via taking advantage of tactful feature partitions across both channel and spatial dimensions, allowing to effectively transfer dense and structured local knowledge learnt by the teacher model to a target student model while maintaining training efficiency. Extensive experiments on five mainstream benchmarks with various teacher-student network pairs demonstrate the effectiveness of our approach. For instance, the DeepLabV3-Res18|DeepLabV3-MBV2 model trained by Af-DCD reaches 77.03%|76.38% mIOU on Cityscapes dataset when choosing DeepLabV3-Res101 as the teacher, setting new performance records. Besides that, Af-DCD achieves an absolute mIOU improvement of 3.26%|3.04%|2.75%|2.30%|1.42% compared with individually trained counterpart on Cityscapes|Pascal VOC|Camvid|ADE20K|COCO-Stuff-164K. Code is available at https://github.com/OSVAI/Af-DCD

arXiv:2312.01006공식 코드 · Papers with Code

Dual-Teacher De-biasing Distillation Framework for Multi-domain Fake News Detection

Multi-domain fake news detection aims to identify whether various news from different domains is real or fake and has become urgent and important. However, existing methods are dedicated to improving the overall performance of fake news detection, ignoring the fact that unbalanced data leads to disparate treatment for different domains, i.e., the domain bias problem. To solve this problem, we propose the Dual-Teacher De-biasing Distillation framework (DTDBD) to mitigate bias across different domains. Following the knowledge distillation methods, DTDBD adopts a teacher-student structure, where pre-trained large teachers instruct a student model. In particular, the DTDBD consists of an unbiased teacher and a clean teacher that jointly guide the student model in mitigating domain bias and maintaining performance. For the unbiased teacher, we introduce an adversarial de-biasing distillation loss to instruct the student model in learning unbiased domain knowledge. For the clean teacher, we design domain knowledge distillation loss, which effectively incentivizes the student model to focus on representing domain features while maintaining performance. Moreover, we present a momentum-based dynamic adjustment algorithm to trade off the effects of two teachers. Extensive experiments on Chinese and English datasets show that the proposed method substantially outperforms the state-of-the-art baseline methods in terms of bias metrics while guaranteeing competitive performance.

arXiv:2312.01338공식 코드 · Papers with Code

Enhancing and Adapting in the Clinic: Source-free Unsupervised Domain Adaptation for Medical Image Enhancement

Medical imaging provides many valuable clues involving anatomical structure and pathological characteristics. However, image degradation is a common issue in clinical practice, which can adversely impact the observation and diagnosis by physicians and algorithms. Although extensive enhancement models have been developed, these models require a well pre-training before deployment, while failing to take advantage of the potential value of inference data after deployment. In this paper, we raise an algorithm for source-free unsupervised domain adaptive medical image enhancement (SAME), which adapts and optimizes enhancement models using test data in the inference phase. A structure-preserving enhancement network is first constructed to learn a robust source model from synthesized training data. Then a teacher-student model is initialized with the source model and conducts source-free unsupervised domain adaptation (SFUDA) by knowledge distillation with the test data. Additionally, a pseudo-label picker is developed to boost the knowledge distillation of enhancement tasks. Experiments were implemented on ten datasets from three medical image modalities to validate the advantage of the proposed algorithm, and setting analysis and ablation studies were also carried out to interpret the effectiveness of SAME. The remarkable enhancement performance and benefits for downstream tasks demonstrate the potential and generalizability of SAME. The code is available at https://github.com/liamheng/Annotation-free-Medical-Image-Enhancement.

arXiv:2305.15712공식 코드 · Papers with Code

Knowledge Diffusion for Distillation

The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature alignments, which are task-specific and feature-specific. In this paper, we state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature, and propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models. Our approach is based on the observation that student features typically contain more noises than teacher features due to the smaller capacity of student model. To address this, we propose to denoise student features using a diffusion model trained by teacher features. This allows us to perform better distillation between the refined clean feature and teacher feature. Additionally, we introduce a light-weight diffusion model with a linear autoencoder to reduce the computation cost and an adaptive noise matching module to improve the denoising performance. Extensive experiments demonstrate that DiffKD is effective across various types of features and achieves state-of-the-art performance consistently on image classification, object detection, and semantic segmentation tasks. Code is available at https://github.com/hunto/DiffKD.

arXiv:2312.00663공식 코드 · Papers with Code

Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment

Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck is that these models do not have the capacity to recognize any unseen novel classes beyond the training categories in diverse real-world applications. Therefore, we are in urgent need of a framework that can simultaneously be applicable to both 3D point cloud segmentation and detection, particularly in the circumstances where the labels are rather scarce. This work presents a generalized and straightforward framework for dealing with 3D scene understanding when the labeled scenes are quite limited. To extract knowledge for novel categories from the pre-trained vision-language models, we propose a hierarchical feature-aligned pre-training and knowledge distillation strategy to extract and distill meaningful information from large-scale vision-language models, which helps benefit the open-vocabulary scene understanding tasks. To encourage latent instance discrimination and to guarantee efficiency, we propose the unsupervised region-level semantic contrastive learning scheme for point clouds, using confident predictions of the neural network to discriminate the intermediate feature embeddings at multiple stages. In the limited reconstruction case, our proposed approach, termed WS3D++, ranks 1st on the large-scale ScanNet benchmark on both the task of semantic segmentation and instance segmentation. Extensive experiments with both indoor and outdoor scenes demonstrated the effectiveness of our approach in both data-efficient learning and open-world few-shot learning. The code is made publicly available at: https://drive.google.com/drive/folders/1M58V-PtR8DBEwD296zJkNg_m2qq-MTAP?usp=sharing.

arXiv:2308.06744공식 코드 · Papers with Code

Token-Scaled Logit Distillation for Ternary Weight Generative Language Models

Generative Language Models (GLMs) have shown impressive performance in tasks such as text generation, understanding, and reasoning. However, the large model size poses challenges for practical deployment. To solve this problem, Quantization-Aware Training (QAT) has become increasingly popular. However, current QAT methods for generative models have resulted in a noticeable loss of accuracy. To counteract this issue, we propose a novel knowledge distillation method specifically designed for GLMs. Our method, called token-scaled logit distillation, prevents overfitting and provides superior learning from the teacher model and ground truth. This research marks the first evaluation of ternary weight quantization-aware training of large-scale GLMs with less than 1.0 degradation in perplexity and achieves enhanced accuracy in tasks like common-sense QA and arithmetic reasoning as well as natural language understanding. Our code is available at https://github.com/aiha-lab/TSLD.

arXiv:2310.19444공식 코드 · Papers with Code

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

Knowledge distillation~(KD) has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. However, most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family, particularly the hint-based approaches. By using centered kernel alignment (CKA) to compare the learned features between heterogeneous teacher and student models, we observe significant feature divergence. This divergence illustrates the ineffectiveness of previous hint-based methods in cross-architecture distillation. To tackle the challenge in distilling heterogeneous models, we propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures. Specifically, we project intermediate features into an aligned latent space such as the logits space, where architecture-specific information is discarded. Additionally, we introduce an adaptive target enhancement scheme to prevent the student from being disturbed by irrelevant information. Extensive experiments with various architectures, including CNN, Transformer, and MLP, demonstrate the superiority of our OFA-KD framework in enabling distillation between heterogeneous architectures. Specifically, when equipped with our OFA-KD, the student models achieve notable performance improvements, with a maximum gain of 8.0% on the CIFAR-100 dataset and 0.7% on the ImageNet-1K dataset. PyTorch code and checkpoints can be found at https://github.com/Hao840/OFAKD.

arXiv:2311.18823공식 코드 · Papers with Code

Initializing Models with Larger Ones

Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch. However, the growing number of pretrained models now offers new opportunities for tackling this classical problem of weight initialization. In this work, we introduce weight selection, a method for initializing smaller models by selecting a subset of weights from a pretrained larger model. This enables the transfer of knowledge from pretrained weights to smaller models. Our experiments demonstrate that weight selection can significantly enhance the performance of small models and reduce their training time. Notably, it can also be used together with knowledge distillation. Weight selection offers a new approach to leverage the power of pretrained models in resource-constrained settings, and we hope it can be a useful tool for training small models in the large-model era. Code is available at https://github.com/OscarXZQ/weight-selection.

arXiv:2310.07403공식 코드 · Papers with Code

DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation

Direct speech-to-speech translation (S2ST) translates speech from one language into another using a single model. However, due to the presence of linguistic and acoustic diversity, the target speech follows a complex multimodal distribution, posing challenges to achieving both high-quality translations and fast decoding speeds for S2ST models. In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST. To better capture the complex distribution of the target speech, DASpeech adopts the two-pass architecture to decompose the generation process into two steps, where a linguistic decoder first generates the target text, and an acoustic decoder then generates the target speech based on the hidden states of the linguistic decoder. Specifically, we use the decoder of DA-Transformer as the linguistic decoder, and use FastSpeech 2 as the acoustic decoder. DA-Transformer models translations with a directed acyclic graph (DAG). To consider all potential paths in the DAG during training, we calculate the expected hidden states for each target token via dynamic programming, and feed them into the acoustic decoder to predict the target mel-spectrogram. During inference, we select the most probable path and take hidden states on that path as input to the acoustic decoder. Experiments on the CVSS Fr-En benchmark demonstrate that DASpeech can achieve comparable or even better performance than the state-of-the-art S2ST model Translatotron 2, while preserving up to 18.53x speedup compared to the autoregressive baseline. Compared with the previous non-autoregressive S2ST model, DASpeech does not rely on knowledge distillation and iterative decoding, achieving significant improvements in both translation quality and decoding speed. Furthermore, DASpeech shows the ability to preserve the speaker's voice of the source speech during translation.

arXiv:2311.17373공식 코드 · Papers with Code

The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation

Graph neural networks (GNNs) are being increasingly used in many high-stakes tasks, and as a result, there is growing attention on their fairness recently. GNNs have been shown to be unfair as they tend to make discriminatory decisions toward certain demographic groups, divided by sensitive attributes such as gender and race. While recent works have been devoted to improving their fairness performance, they often require accessible demographic information. This greatly limits their applicability in real-world scenarios due to legal restrictions. To address this problem, we present a demographic-agnostic method to learn fair GNNs via knowledge distillation, namely FairGKD. Our work is motivated by the empirical observation that training GNNs on partial data (i.e., only node attributes or topology data) can improve their fairness, albeit at the cost of utility. To make a balanced trade-off between fairness and utility performance, we employ a set of fairness experts (i.e., GNNs trained on different partial data) to construct the synthetic teacher, which distills fairer and informative knowledge to guide the learning of the GNN student. Experiments on several benchmark datasets demonstrate that FairGKD, which does not require access to demographic information, significantly improves the fairness of GNNs by a large margin while maintaining their utility.

arXiv:2311.17450공식 코드 · Papers with Code

Continual Learning for Image Segmentation with Dynamic Query

Image segmentation based on continual learning exhibits a critical drop of performance, mainly due to catastrophic forgetting and background shift, as they are required to incorporate new classes continually. In this paper, we propose a simple, yet effective Continual Image Segmentation method with incremental Dynamic Query (CISDQ), which decouples the representation learning of both old and new knowledge with lightweight query embedding. CISDQ mainly includes three contributions: 1) We define dynamic queries with adaptive background class to exploit past knowledge and learn future classes naturally. 2) CISDQ proposes a class/instance-aware Query Guided Knowledge Distillation strategy to overcome catastrophic forgetting by capturing the inter-class diversity and intra-class identity. 3) Apart from semantic segmentation, CISDQ introduce the continual learning for instance segmentation in which instance-wise labeling and supervision are considered. Extensive experiments on three datasets for two tasks (i.e., continual semantic and instance segmentation are conducted to demonstrate that CISDQ achieves the state-of-the-art performance, specifically, obtaining 4.4% and 2.9% mIoU improvements for the ADE 100-10 (6 steps) setting and ADE 100-5 (11 steps) setting.

arXiv:2311.17245공식 코드 · Papers with Code

LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS

Recent advances in real-time neural rendering using point-based techniques have enabled broader adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting impose substantial storage overhead, as Structure-from-Motion (SfM) points can grow to millions, often requiring gigabyte-level disk space for a single unbounded scene. This growth presents scalability challenges and hinders splatting efficiency. To address this, we introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction, and applies a pruning and recovery process to reduce redundancy while preserving visual quality. Knowledge distillation and pseudo-view augmentation then transfer spherical harmonic coefficients to a lower degree, yielding compact representations. Gaussian Vector Quantization, based on each Gaussian's global significance, further lowers bitwidth with minimal accuracy loss. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework, enabling efficient complex scene representation on the Mip-NeRF 360 and Tank & Temple datasets. The proposed Gaussian pruning approach is also adaptable to other 3D representations (e.g., Scaffold-GS), demonstrating strong generalization capabilities.

arXiv:2311.17086공식 코드 · Papers with Code

PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation

Text-to-image diffusion models are well-known for their ability to generate realistic images based on textual prompts. However, the existing works have predominantly focused on English, lacking support for non-English text-to-image models. The most commonly used translation methods cannot solve the generation problem related to language culture, while training from scratch on a specific language dataset is prohibitively expensive. In this paper, we are inspired to propose a simple plug-and-play language transfer method based on knowledge distillation. All we need to do is train a lightweight MLP-like parameter-efficient adapter (PEA) with only 6M parameters under teacher knowledge distillation along with a small parallel data corpus. We are surprised to find that freezing the parameters of UNet can still achieve remarkable performance on the language-specific prompt evaluation set, demonstrating that PEA can stimulate the potential generation ability of the original UNet. Additionally, it closely approaches the performance of the English text-to-image model on a general prompt evaluation set. Furthermore, our adapter can be used as a plugin to achieve significant results in downstream tasks in cross-lingual text-to-image generation. Code will be available at: https://github.com/OPPO-Mente-Lab/PEA-Diffusion

arXiv:2305.08776공식 코드 · Papers with Code

Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models

Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding. However, their potential to enrich 3D scene representation learning is largely untapped due to the existence of the domain gap. In this work, we propose an innovative methodology called Bridge3D to address this gap by pre-training 3D models using features, semantic masks, and captions sourced from foundation models. Specifically, our method employs semantic masks from foundation models to guide the masking and reconstruction process for the masked autoencoder, enabling more focused attention on foreground representations. Moreover, we bridge the 3D-text gap at the scene level using image captioning foundation models, thereby facilitating scene-level knowledge distillation. We further extend this bridging effort by introducing an innovative object-level knowledge distillation method that harnesses highly accurate object-level masks and semantic text data from foundation models. Our methodology significantly surpasses the performance of existing state-of-the-art methods in 3D object detection and semantic segmentation tasks. For instance, on the ScanNet dataset, Bridge3D improves the baseline by a notable margin of 6.3%. Code will be available at: https://github.com/Zhimin-C/Bridge3D

arXiv:2311.16700공식 코드 · Papers with Code

Rethinking Intermediate Layers design in Knowledge Distillation for Kidney and Liver Tumor Segmentation

Knowledge distillation (KD) has demonstrated remarkable success across various domains, but its application to medical imaging tasks, such as kidney and liver tumor segmentation, has encountered challenges. Many existing KD methods are not specifically tailored for these tasks. Moreover, prevalent KD methods often lack a careful consideration of `what' and `from where' to distill knowledge from the teacher to the student. This oversight may lead to issues like the accumulation of training bias within shallower student layers, potentially compromising the effectiveness of KD. To address these challenges, we propose Hierarchical Layer-selective Feedback Distillation (HLFD). HLFD strategically distills knowledge from a combination of middle layers to earlier layers and transfers final layer knowledge to intermediate layers at both the feature and pixel levels. This design allows the model to learn higher-quality representations from earlier layers, resulting in a robust and compact student model. Extensive quantitative evaluations reveal that HLFD outperforms existing methods by a significant margin. For example, in the kidney segmentation task, HLFD surpasses the student model (without KD) by over 10\%, significantly improving its focus on tumor-specific features. From a qualitative standpoint, the student model trained using HLFD excels at suppressing irrelevant information and can focus sharply on tumor-specific details, which opens a new pathway for more efficient and accurate diagnostic tools. Code is available \href{https://github.com/vangorade/RethinkingKD_ISBI24}{here}.

arXiv:2311.15493공식 코드 · Papers with Code

UFIN: Universal Feature Interaction Network for Multi-Domain Click-Through Rate Prediction

Click-Through Rate (CTR) prediction, which aims to estimate the probability of a user clicking on an item, is a key task in online advertising. Numerous existing CTR models concentrate on modeling the feature interactions within a solitary domain, thereby rendering them inadequate for fulfilling the requisites of multi-domain recommendations in real industrial scenarios. Some recent approaches propose intricate architectures to enhance knowledge sharing and augment model training across multiple domains. However, these approaches encounter difficulties when being transferred to new recommendation domains, owing to their reliance on the modeling of ID features (e.g., item id). To address the above issue, we propose the Universal Feature Interaction Network (UFIN) approach for CTR prediction. UFIN exploits textual data to learn universal feature interactions that can be effectively transferred across diverse domains. For learning universal feature representations, we regard the text and feature as two different modalities and propose an encoder-decoder network founded on a Large Language Model (LLM) to enforce the transfer of data from the text modality to the feature modality. Building upon the above foundation, we further develop a mixtureof-experts (MoE) enhanced adaptive feature interaction model to learn transferable collaborative patterns across multiple domains. Furthermore, we propose a multi-domain knowledge distillation framework to enhance feature interaction learning. Based on the above methods, UFIN can effectively bridge the semantic gap to learn common knowledge across various domains, surpassing the constraints of ID-based models. Extensive experiments conducted on eight datasets show the effectiveness of UFIN, in both multidomain and cross-platform settings. Our code is available at https://github.com/RUCAIBox/UFIN.

arXiv:2311.13921공식 코드 · Papers with Code

Some Like It Small: Czech Semantic Embedding Models for Industry Applications

This article focuses on the development and evaluation of Small-sized Czech sentence embedding models. Small models are important components for real-time industry applications in resource-constrained environments. Given the limited availability of labeled Czech data, alternative approaches, including pre-training, knowledge distillation, and unsupervised contrastive fine-tuning, are investigated. Comprehensive intrinsic and extrinsic analyses are conducted, showcasing the competitive performance of our models compared to significantly larger counterparts, with approximately 8 times smaller size and 5 times faster speed than conventional Base-sized models. To promote cooperation and reproducibility, both the models and the evaluation pipeline are made publicly accessible. Ultimately, this article presents practical applications of the developed sentence embedding models in Seznam.cz, the Czech search engine. These models have effectively replaced previous counterparts, enhancing the overall search experience for instance, in organic search, featured snippets, and image search. This transition has yielded improved performance.

arXiv:2311.14160공식 코드 · Papers with Code

Efficient and Robust Jet Tagging at the LHC with Knowledge Distillation

The challenging environment of real-time data processing systems at the Large Hadron Collider (LHC) strictly limits the computational complexity of algorithms that can be deployed. For deep learning models, this implies that only models with low computational complexity that have weak inductive bias are feasible. To address this issue, we utilize knowledge distillation to leverage both the performance of large models and the reduced computational complexity of small ones. In this paper, we present an implementation of knowledge distillation, demonstrating an overall boost in the student models' performance for the task of classifying jets at the LHC. Furthermore, by using a teacher model with a strong inductive bias of Lorentz symmetry, we show that we can induce the same inductive bias in the student model which leads to better robustness against arbitrary Lorentz boost.