PyTorchKR Papers

최신 논문

총 10,240편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2310.20706공식 코드 · Papers with Code

DDAM-PS: Diligent Domain Adaptive Mixer for Person Search

Person search (PS) is a challenging computer vision problem where the objective is to achieve joint optimization for pedestrian detection and re-identification (ReID). Although previous advancements have shown promising performance in the field under fully and weakly supervised learning fashion, there exists a major gap in investigating the domain adaptation ability of PS models. In this paper, we propose a diligent domain adaptive mixer (DDAM) for person search (DDAP-PS) framework that aims to bridge a gap to improve knowledge transfer from the labeled source domain to the unlabeled target domain. Specifically, we introduce a novel DDAM module that generates moderate mixed-domain representations by combining source and target domain representations. The proposed DDAM module encourages domain mixing to minimize the distance between the two extreme domains, thereby enhancing the ReID task. To achieve this, we introduce two bridge losses and a disparity loss. The objective of the two bridge losses is to guide the moderate mixed-domain representations to maintain an appropriate distance from both the source and target domain representations. The disparity loss aims to prevent the moderate mixed-domain representations from being biased towards either the source or target domains, thereby avoiding overfitting. Furthermore, we address the conflict between the two subtasks, localization and ReID, during domain adaptation. To handle this cross-task conflict, we forcefully decouple the norm-aware embedding, which aids in better learning of the moderate mixed-domain representation. We conduct experiments to validate the effectiveness of our proposed method. Our approach demonstrates favorable performance on the challenging PRW and CUHK-SYSU datasets. Our source code is publicly available at \url{https://github.com/mustansarfiaz/DDAM-PS}.

arXiv:2310.20187

Self-Supervised Pre-Training for Precipitation Post-Processor

Obtaining a sufficient forecast lead time for local precipitation is essential in preventing hazardous weather events. Global warming-induced climate change increases the challenge of accurately predicting severe precipitation events, such as heavy rainfall. In this paper, we propose a deep learning-based precipitation post-processor for numerical weather prediction (NWP) models. The precipitation post-processor consists of (i) employing self-supervised pre-training, where the parameters of the encoder are pre-trained on the reconstruction of the masked variables of the atmospheric physics domain; and (ii) conducting transfer learning on precipitation segmentation tasks (the target domain) from the pre-trained encoder. In addition, we introduced a heuristic labeling approach to effectively train class-imbalanced datasets. Our experiments on precipitation correction for regional NWP show that the proposed method outperforms other approaches.

arXiv:2310.19567공식 코드 · Papers with Code

CreoleVal: Multilingual Multitask Benchmarks for Creoles

Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research.While the genealogical ties between Creoles and a number of highly-resourced languages imply a significant potential for transfer learning, this potential is hampered due to this lack of annotated data. In this work we present CreoleVal, a collection of benchmark datasets spanning 8 different NLP tasks, covering up to 28 Creole languages; it is an aggregate of novel development datasets for reading comprehension, relation classification, and machine translation for Creoles, in addition to a practical gateway to a handful of preexisting benchmarks. For each benchmark, we conduct baseline experiments in a zero-shot setting in order to further ascertain the capabilities and limitations of transfer learning for Creoles. Ultimately, we see CreoleVal as an opportunity to empower research on Creoles in NLP and computational linguistics, and in general, a step towards more equitable language technology around the globe.

arXiv:2310.19721공식 코드 · Papers with Code

Promise:Prompt-driven 3D Medical Image Segmentation Using Pretrained Image Foundation Models

To address prevalent issues in medical imaging, such as data acquisition challenges and label availability, transfer learning from natural to medical image domains serves as a viable strategy to produce reliable segmentation results. However, several existing barriers between domains need to be broken down, including addressing contrast discrepancies, managing anatomical variability, and adapting 2D pretrained models for 3D segmentation tasks. In this paper, we propose ProMISe,a prompt-driven 3D medical image segmentation model using only a single point prompt to leverage knowledge from a pretrained 2D image foundation model. In particular, we use the pretrained vision transformer from the Segment Anything Model (SAM) and integrate lightweight adapters to extract depth-related (3D) spatial context without updating the pretrained weights. For robust results, a hybrid network with complementary encoders is designed, and a boundary-aware loss is proposed to achieve precise boundaries. We evaluate our model on two public datasets for colon and pancreas tumor segmentations, respectively. Compared to the state-of-the-art segmentation methods with and without prompt engineering, our proposed method achieves superior performance. The code is publicly available at https://github.com/MedICL-VU/ProMISe.

arXiv:2310.19537

On consequences of finetuning on data with highly discriminative features

In the era of transfer learning, training neural networks from scratch is becoming obsolete. Transfer learning leverages prior knowledge for new tasks, conserving computational resources. While its advantages are well-documented, we uncover a notable drawback: networks tend to prioritize basic data patterns, forsaking valuable pre-learned features. We term this behavior "feature erosion" and analyze its impact on network performance and internal representations.

arXiv:2310.19289공식 코드 · Papers with Code

AMLNet: Adversarial Mutual Learning Neural Network for Non-AutoRegressive Multi-Horizon Time Series Forecasting

Multi-horizon time series forecasting, crucial across diverse domains, demands high accuracy and speed. While AutoRegressive (AR) models excel in short-term predictions, they suffer speed and error issues as the horizon extends. Non-AutoRegressive (NAR) models suit long-term predictions but struggle with interdependence, yielding unrealistic results. We introduce AMLNet, an innovative NAR model that achieves realistic forecasts through an online Knowledge Distillation (KD) approach. AMLNet harnesses the strengths of both AR and NAR models by training a deep AR decoder and a deep NAR decoder in a collaborative manner, serving as ensemble teachers that impart knowledge to a shallower NAR decoder. This knowledge transfer is facilitated through two key mechanisms: 1) outcome-driven KD, which dynamically weights the contribution of KD losses from the teacher models, enabling the shallow NAR decoder to incorporate the ensemble's diversity; and 2) hint-driven KD, which employs adversarial training to extract valuable insights from the model's hidden states for distillation. Extensive experimentation showcases AMLNet's superiority over conventional AR and NAR models, thereby presenting a promising avenue for multi-horizon time series forecasting that enhances accuracy and expedites computation.

arXiv:2310.18356

LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery

Large Language Models (LLMs) have transformed the landscape of artificial intelligence, while their enormous size presents significant challenges in terms of computational costs. We introduce LoRAShear, a novel efficient approach to structurally prune LLMs and recover knowledge. Given general LLMs, LoRAShear at first creates the dependency graphs over LoRA modules to discover minimally removal structures and analyze the knowledge distribution. It then proceeds progressive structured pruning on LoRA adaptors and enables inherent knowledge transfer to better preserve the information in the redundant structures. To recover the lost knowledge during pruning, LoRAShear meticulously studies and proposes a dynamic fine-tuning schemes with dynamic data adaptors to effectively narrow down the performance gap to the full models. Numerical results demonstrate that by only using one GPU within a couple of GPU days, LoRAShear effectively reduced footprint of LLMs by 20% with only 1.0% performance degradation and significantly outperforms state-of-the-arts. The source code will be available at https://github.com/microsoft/lorashear.

arXiv:2310.19545

MENTOR: Human Perception-Guided Pretraining for Increased Generalization

Incorporating human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks. One of the active research questions is where (in the model architecture) and how to efficiently incorporate always-limited human perceptual data into training strategies of models. In this paper, we introduce MENTOR (huMan pErceptioN-guided preTraining fOr increased geneRalization), which addresses this question through two unique rounds of training the CNNs tasked with open-set anomaly detection. First, we train an autoencoder to learn human saliency maps given an input image, without class labels. The autoencoder is thus tasked with discovering domain-specific salient features which mimic human perception. Second, we remove the decoder part, add a classification layer on top of the encoder, and fine-tune this new model conventionally. We show that MENTOR's benefits are twofold: (a) significant accuracy boost in anomaly detection tasks (in this paper demonstrated for detection of unknown iris presentation attacks, synthetically-generated faces, and anomalies in chest X-ray images), compared to models utilizing conventional transfer learning (e.g., sourcing the weights from ImageNet-pretrained models) as well as to models trained with the state-of-the-art approach incorporating human perception guidance into loss functions, and (b) an increase in the efficiency of model training, requiring fewer epochs to converge compared to state-of-the-art training methods.

arXiv:2310.19342공식 코드 · Papers with Code

Label-Only Model Inversion Attacks via Knowledge Transfer

In a model inversion (MI) attack, an adversary abuses access to a machine learning (ML) model to infer and reconstruct private training data. Remarkable progress has been made in the white-box and black-box setups, where the adversary has access to the complete model or the model's soft output respectively. However, there is very limited study in the most challenging but practically important setup: Label-only MI attacks, where the adversary only has access to the model's predicted label (hard label) without confidence scores nor any other model information. In this work, we propose LOKT, a novel approach for label-only MI attacks. Our idea is based on transfer of knowledge from the opaque target model to surrogate models. Subsequently, using these surrogate models, our approach can harness advanced white-box attacks. We propose knowledge transfer based on generative modelling, and introduce a new model, Target model-assisted ACGAN (T-ACGAN), for effective knowledge transfer. Our method casts the challenging label-only MI into the more tractable white-box setup. We provide analysis to support that surrogate models based on our approach serve as effective proxies for the target model for MI. Our experiments show that our method significantly outperforms existing SOTA Label-only MI attack by more than 15% across all MI benchmarks. Furthermore, our method compares favorably in terms of query budget. Our study highlights rising privacy threats for ML models even when minimal information (i.e., hard labels) is exposed. Our study highlights rising privacy threats for ML models even when minimal information (i.e., hard labels) is exposed. Our code, demo, models and reconstructed data are available at our project page: https://ngoc-nguyen-0.github.io/lokt/

arXiv:2310.19232

Adapter Pruning using Tropical Characterization

Adapters are widely popular parameter-efficient transfer learning approaches in natural language processing that insert trainable modules in between layers of a pre-trained language model. Apart from several heuristics, however, there has been a lack of studies analyzing the optimal number of adapter parameters needed for downstream applications. In this paper, we propose an adapter pruning approach by studying the tropical characteristics of trainable modules. We cast it as an optimization problem that aims to prune parameters from the adapter layers without changing the orientation of underlying tropical hypersurfaces. Our experiments on five NLP datasets show that tropical geometry tends to identify more relevant parameters to prune when compared with the magnitude-based baseline, while a combined approach works best across the tasks.

arXiv:2310.18472

Parameter-Efficient Methods for Metastases Detection from Clinical Notes

Understanding the progression of cancer is crucial for defining treatments for patients. The objective of this study is to automate the detection of metastatic liver disease from free-style computed tomography (CT) radiology reports. Our research demonstrates that transferring knowledge using three approaches can improve model performance. First, we utilize generic language models (LMs), pretrained in a self-supervised manner. Second, we use a semi-supervised approach to train our model by automatically annotating a large unlabeled dataset; this approach substantially enhances the model's performance. Finally, we transfer knowledge from related tasks by designing a multi-task transfer learning methodology. We leverage the recent advancement of parameter-efficient LM adaptation strategies to improve performance and training efficiency. Our dataset consists of CT reports collected at Memorial Sloan Kettering Cancer Center (MSKCC) over the course of 12 years. 2,641 reports were manually annotated by domain experts; among them, 841 reports have been annotated for the presence of liver metastases. Our best model achieved an F1-score of 73.8%, a precision of 84%, and a recall of 65.8%.

arXiv:2310.19168공식 코드 · Papers with Code

BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping

We propose a metadata-aware self-supervised learning~(SSL)~framework useful for fine-grained classification and ecological mapping of bird species around the world. Our framework unifies two SSL strategies: Contrastive Learning~(CL) and Masked Image Modeling~(MIM), while also enriching the embedding space with metadata available with ground-level imagery of birds. We separately train uni-modal and cross-modal ViT on a novel cross-view global bird species dataset containing ground-level imagery, metadata (location, time), and corresponding satellite imagery. We demonstrate that our models learn fine-grained and geographically conditioned features of birds, by evaluating on two downstream tasks: fine-grained visual classification~(FGVC) and cross-modal retrieval. Pre-trained models learned using our framework achieve SotA performance on FGVC of iNAT-2021 birds and in transfer learning settings for CUB-200-2011 and NABirds datasets. Moreover, the impressive cross-modal retrieval performance of our model enables the creation of species distribution maps across any geographic region. The dataset and source code will be released at https://github.com/mvrl/BirdSAT}.

arXiv:2310.19159

Transfer Learning in Transformer-Based Demand Forecasting For Home Energy Management System

Increasingly, homeowners opt for photovoltaic (PV) systems and/or battery storage to minimize their energy bills and maximize renewable energy usage. This has spurred the development of advanced control algorithms that maximally achieve those goals. However, a common challenge faced while developing such controllers is the unavailability of accurate forecasts of household power consumption, especially for shorter time resolutions (15 minutes) and in a data-efficient manner. In this paper, we analyze how transfer learning can help by exploiting data from multiple households to improve a single house's load forecasting. Specifically, we train an advanced forecasting model (a temporal fusion transformer) using data from multiple different households, and then finetune this global model on a new household with limited data (i.e. only a few days). The obtained models are used for forecasting power consumption of the household for the next 24 hours~(day-ahead) at a time resolution of 15 minutes, with the intention of using these forecasts in advanced controllers such as Model Predictive Control. We show the benefit of this transfer learning setup versus solely using the individual new household's data, both in terms of (i) forecasting accuracy ($\sim$15\% MAE reduction) and (ii) control performance ($\sim$2\% energy cost reduction), using real-world household data.

arXiv:2310.18928

A transfer learning approach with convolutional neural network for Face Mask Detection

Due to the epidemic of the coronavirus (Covid-19) and its rapid spread around the world, the world has faced an enormous crisis. To prevent the spread of the coronavirus, the World Health Organization (WHO) has introduced the use of masks and keeping social distance as the best preventive method. So, developing an automatic monitoring system for detecting facemasks in some crowded places is essential. To do this, we propose a mask recognition system based on transfer learning and Inception v3 architecture. In the proposed method, two datasets are used simultaneously for training including the Simulated Mask Face Dataset (SMFD) and MaskedFace-Net (MFN) This paper tries to increase the accuracy of the proposed system by optimally setting hyper-parameters and accurately designing the fully connected layers. The main advantage of the proposed method is that in addition to masked and unmasked faces, it can also detect cases of incorrect use of mask. Therefore, the proposed method classifies the input face images into three categories. Experimental results show the high accuracy and efficiency of the proposed method; so, this method has achieved an accuracy of 99.47% and 99.33% in training and test data respectively

arXiv:2310.18885

A foundational neural operator that continuously learns without forgetting

Machine learning has witnessed substantial growth, leading to the development of advanced artificial intelligence models crafted to address a wide range of real-world challenges spanning various domains, such as computer vision, natural language processing, and scientific computing. Nevertheless, the creation of custom models for each new task remains a resource-intensive undertaking, demanding considerable computational time and memory resources. In this study, we introduce the concept of the Neural Combinatorial Wavelet Neural Operator (NCWNO) as a foundational model for scientific computing. This model is specifically designed to excel in learning from a diverse spectrum of physics and continuously adapt to the solution operators associated with parametric partial differential equations (PDEs). The NCWNO leverages a gated structure that employs local wavelet experts to acquire shared features across multiple physical systems, complemented by a memory-based ensembling approach among these local wavelet experts. This combination enables rapid adaptation to new challenges. The proposed foundational model offers two key advantages: (i) it can simultaneously learn solution operators for multiple parametric PDEs, and (ii) it can swiftly generalize to new parametric PDEs with minimal fine-tuning. The proposed NCWNO is the first foundational operator learning algorithm distinguished by its (i) robustness against catastrophic forgetting, (ii) the maintenance of positive transfer for new parametric PDEs, and (iii) the facilitation of knowledge transfer across dissimilar tasks. Through an extensive set of benchmark examples, we demonstrate that the NCWNO can outperform task-specific baseline operator learning frameworks with minimal hyperparameter tuning at the prediction stage. We also show that with minimal fine-tuning, the NCWNO performs accurate combinatorial learning of new parametric PDEs.

arXiv:2310.18620공식 코드 · Papers with Code

ODM3D: Alleviating Foreground Sparsity for Semi-Supervised Monocular 3D Object Detection

Monocular 3D object detection (M3OD) is a significant yet inherently challenging task in autonomous driving due to absence of explicit depth cues in a single RGB image. In this paper, we strive to boost currently underperforming monocular 3D object detectors by leveraging an abundance of unlabelled data via semi-supervised learning. Our proposed ODM3D framework entails cross-modal knowledge distillation at various levels to inject LiDAR-domain knowledge into a monocular detector during training. By identifying foreground sparsity as the main culprit behind existing methods' suboptimal training, we exploit the precise localisation information embedded in LiDAR points to enable more foreground-attentive and efficient distillation via the proposed BEV occupancy guidance mask, leading to notably improved knowledge transfer and M3OD performance. Besides, motivated by insights into why existing cross-modal GT-sampling techniques fail on our task at hand, we further design a novel cross-modal object-wise data augmentation strategy for effective RGB-LiDAR joint learning. Our method ranks 1st in both KITTI validation and test benchmarks, significantly surpassing all existing monocular methods, supervised or semi-supervised, on both BEV and 3D detection metrics.

arXiv:2310.18921공식 코드 · Papers with Code

QWID: Quantized Weed Identification Deep neural network

In this paper, we present an efficient solution for weed classification in agriculture. We focus on optimizing model performance at inference while respecting the constraints of the agricultural domain. We propose a Quantized Deep Neural Network model that classifies a dataset of 9 weed classes using 8-bit integer (int8) quantization, a departure from standard 32-bit floating point (fp32) models. Recognizing the hardware resource limitations in agriculture, our model balances model size, inference time, and accuracy, aligning with practical requirements. We evaluate the approach on ResNet-50 and InceptionV3 architectures, comparing their performance against their int8 quantized versions. Transfer learning and fine-tuning are applied using the DeepWeeds dataset. The results show staggering model size and inference time reductions while maintaining accuracy in real-world production scenarios like Desktop, Mobile and Raspberry Pi. Our work sheds light on a promising direction for efficient AI in agriculture, holding potential for broader applications. Code: https://github.com/parikshit14/QNN-for-weed

arXiv:2310.18377

Large-scale Foundation Models and Generative AI for BigData Neuroscience

Recent advances in machine learning have made revolutionary breakthroughs in computer games, image and natural language understanding, and scientific discovery. Foundation models and large-scale language models (LLMs) have recently achieved human-like intelligence thanks to BigData. With the help of self-supervised learning (SSL) and transfer learning, these models may potentially reshape the landscapes of neuroscience research and make a significant impact on the future. Here we present a mini-review on recent advances in foundation models and generative AI models as well as their applications in neuroscience, including natural language and speech, semantic memory, brain-machine interfaces (BMIs), and data augmentation. We argue that this paradigm-shift framework will open new avenues for many neuroscience research directions and discuss the accompanying challenges and opportunities.

arXiv:2310.18373

Can LLMs Grade Short-Answer Reading Comprehension Questions : An Empirical Study with a Novel Dataset

Open-ended questions, which require students to produce multi-word, nontrivial responses, are a popular tool for formative assessment as they provide more specific insights into what students do and don't know. However, grading open-ended questions can be time-consuming leading teachers to resort to simpler question formats or conduct fewer formative assessments. While there has been a longstanding interest in automating of short-answer grading (ASAG), but previous approaches have been technically complex, limiting their use in formative assessment contexts. The newest generation of Large Language Models (LLMs) potentially makes grading short answer questions more feasible. This paper investigates the potential for the newest version of LLMs to be used in ASAG, specifically in the grading of short answer questions for formative assessments, in two ways. First, it introduces a novel dataset of short answer reading comprehension questions, drawn from a set of reading assessments conducted with over 150 students in Ghana. This dataset allows for the evaluation of LLMs in a new context, as they are predominantly designed and trained on data from high-income North American countries. Second, the paper empirically evaluates how well various configurations of generative LLMs grade student short answer responses compared to expert human raters. The findings show that GPT-4, with minimal prompt engineering, performed extremely well on grading the novel dataset (QWK 0.92, F1 0.89), reaching near parity with expert human raters. To our knowledge this work is the first to empirically evaluate the performance of generative LLMs on short answer reading comprehension questions using real student data, with low technical hurdles to attaining this performance. These findings suggest that generative LLMs could be used to grade formative literacy assessment tasks.

arXiv:2310.19137

Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning

Reinforcement learning (RL) is a powerful tool for finding optimal policies in sequential decision processes. However, deep RL methods have two weaknesses: collecting the amount of agent experience required for practical RL problems is prohibitively expensive, and the learned policies exhibit poor generalization on tasks outside the training data distribution. To mitigate these issues, we introduce automaton distillation, a form of neuro-symbolic transfer learning in which Q-value estimates from a teacher are distilled into a low-dimensional representation in the form of an automaton. We then propose methods for generating Q-value estimates where symbolic information is extracted from a teacher's Deep Q-Network (DQN). The resulting Q-value estimates are used to bootstrap learning in the target discrete and continuous environment via a modified DQN and Twin-Delayed Deep Deterministic (TD3) loss function, respectively. We demonstrate that automaton distillation decreases the time required to find optimal policies for various decision tasks in new environments, even in a target environment different in structure from the source environment.