PyTorchKR Papers

최신 논문

총 4,526편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2306.02027공식 코드 · Papers with Code

Evolving Knowledge Mining for Class Incremental Segmentation

Class Incremental Semantic Segmentation (CISS) has been a trend recently due to its great significance in real-world applications. Although the existing CISS methods demonstrate remarkable performance, they either leverage the high-level knowledge (feature) only while neglecting the rich and diverse knowledge in the low-level features, leading to poor old knowledge preservation and weak new knowledge exploration; or use multi-level features for knowledge distillation by retraining a heavy backbone, which is computationally intensive. In this paper, we for the first time investigate the efficient multi-grained knowledge reuse for CISS, and propose a novel method, Evolving kNowleDge minING (ENDING), employing a frozen backbone. ENDING incorporates two key modules: evolving fusion and semantic enhancement, for dynamic and comprehensive exploration of multi-grained knowledge. Evolving fusion is tailored to extract knowledge from individual low-level feature using a personalized lightweight network, which is generated from a meta-net, taking the high-level feature as input. This design enables the evolution of knowledge mining and fusing when applied to incremental new classes. In contrast, semantic enhancement is specifically crafted to aggregate prototype-based semantics from multi-level features, contributing to an enhanced representation. We evaluate our method on two widely used benchmarks and consistently demonstrate new state-of-the-art performance. The code is available at https://github.com/zhiheLu/ENDING_ISS.

arXiv:2306.02921

Zero shot framework for satellite image restoration

Satellite images are typically subject to multiple distortions. Different factors affect the quality of satellite images, including changes in atmosphere, surface reflectance, sun illumination, viewing geometries etc., limiting its application to downstream tasks. In supervised networks, the availability of paired datasets is a strong assumption. Consequently, many unsupervised algorithms have been proposed to address this problem. These methods synthetically generate a large dataset of degraded images using image formation models. A neural network is then trained with an adversarial loss to discriminate between images from distorted and clean domains. However, these methods yield suboptimal performance when tested on real images that do not necessarily conform to the generation mechanism. Also, they require a large amount of training data and are rendered unsuitable when only a few images are available. We propose a distortion disentanglement and knowledge distillation framework for satellite image restoration to address these important issues. Our algorithm requires only two images: the distorted satellite image to be restored and a reference image with similar semantics. Specifically, we first propose a mechanism to disentangle distortion. This enables us to generate images with varying degrees of distortion using the disentangled distortion and the reference image. We then propose the use of knowledge distillation to train a restoration network using the generated image pairs. As a final step, the distorted image is passed through the restoration network to get the final output. Ablation studies show that our proposed mechanism successfully disentangles distortion.

arXiv:2306.02090공식 코드 · Papers with Code

Deep Classifier Mimicry without Data Access

Access to pre-trained models has recently emerged as a standard across numerous machine learning domains. Unfortunately, access to the original data the models were trained on may not equally be granted. This makes it tremendously challenging to fine-tune, compress models, adapt continually, or to do any other type of data-driven update. We posit that original data access may however not be required. Specifically, we propose Contrastive Abductive Knowledge Extraction (CAKE), a model-agnostic knowledge distillation procedure that mimics deep classifiers without access to the original data. To this end, CAKE generates pairs of noisy synthetic samples and diffuses them contrastively toward a model's decision boundary. We empirically corroborate CAKE's effectiveness using several benchmark datasets and various architectural choices, paving the way for broad application.

arXiv:2306.01327

Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23

This paper describes the submission of the UPC Machine Translation group to the IWSLT 2023 Offline Speech Translation task. Our Speech Translation systems utilize foundation models for speech (wav2vec 2.0) and text (mBART50). We incorporate a Siamese pretraining step of the speech and text encoders with CTC and Optimal Transport, to adapt the speech representations to the space of the text model, thus maximizing transfer learning from MT. After this pretraining, we fine-tune our system end-to-end on ST, with Cross Entropy and Knowledge Distillation. Apart from the available ST corpora, we create synthetic data with SegAugment to better adapt our models to the custom segmentations of the IWSLT test sets. Our best single model obtains 31.2 BLEU points on MuST-C tst-COMMON, 29.8 points on IWLST.tst2020 and 33.4 points on the newly released IWSLT.ACLdev2023.

arXiv:2306.01322

Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model without exposing it to identifiable data. Here, we are interested in the privacy issue faced by a data provider who wishes to share their data via a multimodal generative model. A question that immediately arises is ``How can a data provider ensure that the generative model is not leaking identifiable information about a patient?''. Our solution consists of (1) training a first diffusion model on real data (2) generating a synthetic dataset using this model and filtering it to exclude images with a re-identifiability risk (3) training a second diffusion model on the filtered synthetic data only. We showcase that datasets sampled from models trained with privacy distillation can effectively reduce re-identification risk whilst maintaining downstream performance.

arXiv:2306.01526공식 코드 · Papers with Code

Group channel pruning and spatial attention distilling for object detection

Due to the over-parameterization of neural networks, many model compression methods based on pruning and quantization have emerged. They are remarkable in reducing the size, parameter number, and computational complexity of the model. However, most of the models compressed by such methods need the support of special hardware and software, which increases the deployment cost. Moreover, these methods are mainly used in classification tasks, and rarely directly used in detection tasks. To address these issues, for the object detection network we introduce a three-stage model compression method: dynamic sparse training, group channel pruning, and spatial attention distilling. Firstly, to select out the unimportant channels in the network and maintain a good balance between sparsity and accuracy, we put forward a dynamic sparse training method, which introduces a variable sparse rate, and the sparse rate will change with the training process of the network. Secondly, to reduce the effect of pruning on network accuracy, we propose a novel pruning method called group channel pruning. In particular, we divide the network into multiple groups according to the scales of the feature layer and the similarity of module structure in the network, and then we use different pruning thresholds to prune the channels in each group. Finally, to recover the accuracy of the pruned network, we use an improved knowledge distillation method for the pruned network. Especially, we extract spatial attention information from the feature maps of specific scales in each group as knowledge for distillation. In the experiments, we use YOLOv4 as the object detection network and PASCAL VOC as the training dataset. Our method reduces the parameters of the model by 64.7 % and the calculation by 34.9%.

arXiv:2306.00789

Improved Cross-Lingual Transfer Learning For Automatic Speech Translation

Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text translation via semantic knowledge distillation. We show that by initializing the encoder of the encoder-decoder sequence-to-sequence translation model with SAMU-XLS-R, a multilingual speech transformer encoder trained using multi-modal (speech-text) semantic knowledge distillation, we achieve significantly better cross-lingual task knowledge transfer than the baseline XLS-R, a multilingual speech transformer encoder trained via self-supervised learning. We demonstrate the effectiveness of our approach on two popular datasets, namely, CoVoST-2 and Europarl. On the 21 translation tasks of the CoVoST-2 benchmark, we achieve an average improvement of 12.8 BLEU points over the baselines. In the zero-shot translation scenario, we achieve an average gain of 18.8 and 11.9 average BLEU points on unseen medium and low-resource languages. We make similar observations on Europarl speech translation benchmark.

arXiv:2306.00393공식 코드 · Papers with Code

Teacher Agent: A Knowledge Distillation-Free Framework for Rehearsal-based Video Incremental Learning

Rehearsal-based video incremental learning often employs knowledge distillation to mitigate catastrophic forgetting of previously learned data. However, this method faces two major challenges for video task: substantial computing resources from loading teacher model and limited replay capability from performance-limited teacher model. To address these problems, we first propose a knowledge distillation-free framework for rehearsal-based video incremental learning called \textit{Teacher Agent}. Instead of loading parameter-heavy teacher networks, we introduce an agent generator that is either parameter-free or uses only a few parameters to obtain accurate and reliable soft labels. This method not only greatly reduces the computing requirement but also circumvents the problem of knowledge misleading caused by inaccurate predictions of the teacher model. Moreover, we put forward a self-correction loss which provides an effective regularization signal for the review of old knowledge, which in turn alleviates the problem of catastrophic forgetting. Further, to ensure that the samples in the memory buffer are memory-efficient and representative, we introduce a unified sampler for rehearsal-based video incremental learning to mine fixed-length key video frames. Interestingly, based on the proposed strategies, the network exhibits a high level of robustness against spatial resolution reduction when compared to the baseline. Extensive experiments demonstrate the advantages of our method, yielding significant performance improvements while utilizing only half the spatial resolution of video clips as network inputs in the incremental phases.

arXiv:2305.19549

Accurate and Structured Pruning for Efficient Automatic Speech Recognition

Automatic Speech Recognition (ASR) has seen remarkable advancements with deep neural networks, such as Transformer and Conformer. However, these models typically have large model sizes and high inference costs, posing a challenge to deploy on resource-limited devices. In this paper, we propose a novel compression strategy that leverages structured pruning and knowledge distillation to reduce the model size and inference cost of the Conformer model while preserving high recognition performance. Our approach utilizes a set of binary masks to indicate whether to retain or prune each Conformer module, and employs L0 regularization to learn the optimal mask values. To further enhance pruning performance, we use a layerwise distillation strategy to transfer knowledge from unpruned to pruned models. Our method outperforms all pruning baselines on the widely used LibriSpeech benchmark, achieving a 50% reduction in model size and a 28% reduction in inference cost with minimal performance loss.

arXiv:2305.19502공식 코드 · Papers with Code

Graph Entropy Minimization for Semi-supervised Node Classification

Node classifiers are required to comprehensively reduce prediction errors, training resources, and inference latency in the industry. However, most graph neural networks (GNN) concentrate only on one or two of them. The compromised aspects thus are the shortest boards on the bucket, hindering their practical deployments for industrial-level tasks. This work proposes a novel semi-supervised learning method termed Graph Entropy Minimization (GEM) to resolve the three issues simultaneously. GEM benefits its one-hop aggregation from massive uncategorized nodes, making its prediction accuracy comparable to GNNs with two or more hops message passing. It can be decomposed to support stochastic training with mini-batches of independent edge samples, achieving extremely fast sampling and space-saving training. While its one-hop aggregation is faster in inference than deep GNNs, GEM can be further accelerated to an extreme by deriving a non-hop classifier via online knowledge distillation. Thus, GEM can be a handy choice for latency-restricted and error-sensitive services running on resource-constraint hardware. Code is available at https://github.com/cf020031308/GEM.

arXiv:2305.19472공식 코드 · Papers with Code

PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning

Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense knowledge to reason about complex and often contextualized situations, e.g. ``scheduling a doctor's appointment without a phone''. While current approaches show encouraging results using large language models (LLMs), they are hindered by drawbacks such as costly API calls and reproducibility issues. In this paper, we advocate planning using smaller language models. We present PlaSma, a novel two-pronged approach to endow small language models with procedural knowledge and (constrained) language planning capabilities. More concretely, we develop symbolic procedural knowledge distillation to enhance the commonsense knowledge in small language models and an inference-time algorithm to facilitate more structured and accurate reasoning. In addition, we introduce a new related task, Replanning, that requires a revision of a plan to cope with a constrained situation. In both the planning and replanning settings, we show that orders-of-magnitude smaller models (770M-11B parameters) can compete and often surpass their larger teacher models' capabilities. Finally, we showcase successful application of PlaSma in an embodied environment, VirtualHome.

arXiv:2305.19412공식 코드 · Papers with Code

Are Large Kernels Better Teachers than Transformers for ConvNets?

This paper reveals a new appeal of the recently emerged large-kernel Convolutional Neural Networks (ConvNets): as the teacher in Knowledge Distillation (KD) for small-kernel ConvNets. While Transformers have led state-of-the-art (SOTA) performance in various fields with ever-larger models and labeled data, small-kernel ConvNets are considered more suitable for resource-limited applications due to the efficient convolution operation and compact weight sharing. KD is widely used to boost the performance of small-kernel ConvNets. However, previous research shows that it is not quite effective to distill knowledge (e.g., global information) from Transformers to small-kernel ConvNets, presumably due to their disparate architectures. We hereby carry out a first-of-its-kind study unveiling that modern large-kernel ConvNets, a compelling competitor to Vision Transformers, are remarkably more effective teachers for small-kernel ConvNets, due to more similar architectures. Our findings are backed up by extensive experiments on both logit-level and feature-level KD ``out of the box", with no dedicated architectural nor training recipe modifications. Notably, we obtain the \textbf{best-ever pure ConvNet} under 30M parameters with \textbf{83.1\%} top-1 accuracy on ImageNet, outperforming current SOTA methods including ConvNeXt V2 and Swin V2. We also find that beneficial characteristics of large-kernel ConvNets, e.g., larger effective receptive fields, can be seamlessly transferred to students through this large-to-small kernel distillation. Code is available at: \url{https://github.com/VITA-Group/SLaK}.

arXiv:2305.18464공식 코드 · Papers with Code

Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective

Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most works in RL operate in simulated environments where privileged knowledge (e.g., dynamics, surroundings, terrains) is readily available. Conversely, in real-world scenarios, robot agents usually rely solely on local states (e.g., proprioceptive feedback of robot joints) to select actions, leading to a significant sim-to-real gap. Existing methods address this gap by either gradually reducing the reliance on privileged knowledge or performing a two-stage policy imitation. However, we argue that these methods are limited in their ability to fully leverage the available privileged knowledge, resulting in suboptimal performance. In this paper, we formulate the sim-to-real gap as an information bottleneck problem and therefore propose a novel privileged knowledge distillation method called the Historical Information Bottleneck (HIB). In particular, HIB learns a privileged knowledge representation from historical trajectories by capturing the underlying changeable dynamic information. Theoretical analysis shows that the learned privileged knowledge representation helps reduce the value discrepancy between the oracle and learned policies. Empirical experiments on both simulated and real-world tasks demonstrate that HIB yields improved generalizability compared to previous methods. Videos of real-world experiments are available at https://sites.google.com/view/history-ib .

arXiv:2305.18880

Research on Multilingual News Clustering Based on Cross-Language Word Embeddings

Classifying the same event reported by different countries is of significant importance for public opinion control and intelligence gathering. Due to the diverse types of news, relying solely on transla-tors would be costly and inefficient, while depending solely on translation systems would incur considerable performance overheads in invoking translation interfaces and storing translated texts. To address this issue, we mainly focus on the clustering problem of cross-lingual news. To be specific, we use a combination of sentence vector representations of news headlines in a mixed semantic space and the topic probability distributions of news content to represent a news article. In the training of cross-lingual models, we employ knowledge distillation techniques to fit two semantic spaces into a mixed semantic space. We abandon traditional static clustering methods like K-Means and AGNES in favor of the incremental clustering algorithm Single-Pass, which we further modify to better suit cross-lingual news clustering scenarios. Our main contributions are as follows: (1) We adopt the English standard BERT as the teacher model and XLM-Roberta as the student model, training a cross-lingual model through knowledge distillation that can represent sentence-level bilingual texts in both Chinese and English. (2) We use the LDA topic model to represent news as a combina-tion of cross-lingual vectors for headlines and topic probability distributions for con-tent, introducing concepts such as topic similarity to address the cross-lingual issue in news content representation. (3) We adapt the Single-Pass clustering algorithm for the news context to make it more applicable. Our optimizations of Single-Pass include ad-justing the distance algorithm between samples and clusters, adding cluster merging operations, and incorporating a news time parameter.

arXiv:2305.18679

KEYword based Sampling (KEYS) for Large Language Models

Question answering (Q/A) can be formulated as a generative task (Mitra, 2017) where the task is to generate an answer given the question and the passage (knowledge, if available). Recent advances in QA task is focused a lot on language model advancements and less on other areas such as sampling(Krishna et al., 2021), (Nakano et al., 2021). Keywords play very important role for humans in language generation. (Humans formulate keywords and use grammar to connect those keywords and work). In the research community, very little focus is on how humans generate answers to a question and how this behavior can be incorporated in a language model. In this paper, we want to explore these two areas combined, i.e., how sampling can be to used generate answers which are close to human-like behavior and factually correct. Hence, the type of decoding algorithm we think should be used for Q/A tasks should also depend on the keywords. These keywords can be obtained from the question, passage or internet results. We use knowledge distillation techniques to extract keywords and sample using these extracted keywords on top of vanilla decoding algorithms when formulating the answer to generate a human-like answer. In this paper, we show that our decoding method outperforms most commonly used decoding methods for Q/A task

arXiv:2305.18988

A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation

Sketch-Based Image Retrieval (SBIR) is a crucial task in multimedia retrieval, where the goal is to retrieve a set of images that match a given sketch query. Researchers have already proposed several well-performing solutions for this task, but most focus on enhancing embedding through different approaches such as triplet loss, quadruplet loss, adding data augmentation, and using edge extraction. In this work, we tackle the problem from various angles. We start by examining the training data quality and show some of its limitations. Then, we introduce a Relative Triplet Loss (RTL), an adapted triplet loss to overcome those limitations through loss weighting based on anchors similarity. Through a series of experiments, we demonstrate that replacing a triplet loss with RTL outperforms previous state-of-the-art without the need for any data augmentation. In addition, we demonstrate why batch normalization is more suited for SBIR embeddings than l2-normalization and show that it improves significantly the performance of our models. We further investigate the capacity of models required for the photo and sketch domains and demonstrate that the photo encoder requires a higher capacity than the sketch encoder, which validates the hypothesis formulated in [34]. Then, we propose a straightforward approach to train small models, such as ShuffleNetv2 [22] efficiently with a marginal loss of accuracy through knowledge distillation. The same approach used with larger models enabled us to outperform previous state-of-the-art results and achieve a recall of 62.38% at k = 1 on The Sketchy Database [30].

arXiv:2305.18830공식 코드 · Papers with Code

Semi-supervised Pathological Image Segmentation via Cross Distillation of Multiple Attentions

Segmentation of pathological images is a crucial step for accurate cancer diagnosis. However, acquiring dense annotations of such images for training is labor-intensive and time-consuming. To address this issue, Semi-Supervised Learning (SSL) has the potential for reducing the annotation cost, but it is challenged by a large number of unlabeled training images. In this paper, we propose a novel SSL method based on Cross Distillation of Multiple Attentions (CDMA) to effectively leverage unlabeled images. Firstly, we propose a Multi-attention Tri-branch Network (MTNet) that consists of an encoder and a three-branch decoder, with each branch using a different attention mechanism that calibrates features in different aspects to generate diverse outputs. Secondly, we introduce Cross Decoder Knowledge Distillation (CDKD) between the three decoder branches, allowing them to learn from each other's soft labels to mitigate the negative impact of incorrect pseudo labels in training. Additionally, uncertainty minimization is applied to the average prediction of the three branches, which further regularizes predictions on unlabeled images and encourages inter-branch consistency. Our proposed CDMA was compared with eight state-of-the-art SSL methods on the public DigestPath dataset, and the experimental results showed that our method outperforms the other approaches under different annotation ratios. The code is available at \href{https://github.com/HiLab-git/CDMA}{https://github.com/HiLab-git/CDMA.}

arXiv:2305.18413공식 코드 · Papers with Code

Learning to Learn from APIs: Black-Box Data-Free Meta-Learning

Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data. Existing DFML work can only meta-learn from (i) white-box and (ii) small-scale pre-trained models (iii) with the same architecture, neglecting the more practical setting where the users only have inference access to the APIs with arbitrary model architectures and model scale inside. To solve this issue, we propose a Bi-level Data-free Meta Knowledge Distillation (BiDf-MKD) framework to transfer more general meta knowledge from a collection of black-box APIs to one single meta model. Specifically, by just querying APIs, we inverse each API to recover its training data via a zero-order gradient estimator and then perform meta-learning via a novel bi-level meta knowledge distillation structure, in which we design a boundary query set recovery technique to recover a more informative query set near the decision boundary. In addition, to encourage better generalization within the setting of limited API budgets, we propose task memory replay to diversify the underlying task distribution by covering more interpolated tasks. Extensive experiments in various real-world scenarios show the superior performance of our BiDf-MKD framework.

arXiv:2305.17394공식 코드 · Papers with Code

One-Step Knowledge Distillation and Fine-Tuning in Using Large Pre-Trained Self-Supervised Learning Models for Speaker Verification

The application of speech self-supervised learning (SSL) models has achieved remarkable performance in speaker verification (SV). However, there is a computational cost hurdle in employing them, which makes development and deployment difficult. Several studies have simply compressed SSL models through knowledge distillation (KD) without considering the target task. Consequently, these methods could not extract SV-tailored features. This paper suggests One-Step Knowledge Distillation and Fine-Tuning (OS-KDFT), which incorporates KD and fine-tuning (FT). We optimize a student model for SV during KD training to avert the distillation of inappropriate information for the SV. OS-KDFT could downsize Wav2Vec 2.0 based ECAPA-TDNN size by approximately 76.2%, and reduce the SSL model's inference time by 79% while presenting an EER of 0.98%. The proposed OS-KDFT is validated across VoxCeleb1 and VoxCeleb2 datasets and W2V2 and HuBERT SSL models. Experiments are available on our GitHub.

arXiv:2305.17651공식 코드 · Papers with Code

DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models

Self-supervised learning (SSL) has achieved notable success in many speech processing tasks, but the large model size and heavy computational cost hinder the deployment. Knowledge distillation trains a small student model to mimic the behavior of a large teacher model. However, the student architecture usually needs to be manually designed and will remain fixed during training, which requires prior knowledge and can lead to suboptimal performance. Inspired by recent success of task-specific structured pruning, we propose DPHuBERT, a novel task-agnostic compression method for speech SSL based on joint distillation and pruning. Experiments on SUPERB show that DPHuBERT outperforms pure distillation methods in almost all tasks. Moreover, DPHuBERT requires little training time and performs well with limited training data, making it suitable for resource-constrained applications. Our method can also be applied to various speech SSL models. Our code and models will be publicly available.