PyTorchKR Papers

최신 논문

총 395편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2501.14932

Explaining Categorical Feature Interactions Using Graph Covariance and LLMs

Modern datasets often consist of numerous samples with abundant features and associated timestamps. Analyzing such datasets to uncover underlying events typically requires complex statistical methods and substantial domain expertise. A notable example, and the primary data focus of this paper, is the global synthetic dataset from the Counter Trafficking Data Collaborative (CTDC) -- a global hub of human trafficking data containing over 200,000 anonymized records spanning from 2002 to 2022, with numerous categorical features for each record. In this paper, we propose a fast and scalable method for analyzing and extracting significant categorical feature interactions, and querying large language models (LLMs) to generate data-driven insights that explain these interactions. Our approach begins with a binarization step for categorical features using one-hot encoding, followed by the computation of graph covariance at each time. This graph covariance quantifies temporal changes in dependence structures within categorical data and is established as a consistent dependence measure under the Bernoulli distribution. We use this measure to identify significant feature pairs, such as those with the most frequent trends over time or those exhibiting sudden spikes in dependence at specific moments. These extracted feature pairs, along with their timestamps, are subsequently passed to an LLM tasked with generating potential explanations of the underlying events driving these dependence changes. The effectiveness of our method is demonstrated through extensive simulations, and its application to the CTDC dataset reveals meaningful feature pairs and potential data stories underlying the observed feature interactions.

arXiv:2501.09893

Sparse Binary Representation Learning for Knowledge Tracing

Knowledge tracing (KT) models aim to predict students' future performance based on their historical interactions. Most existing KT models rely exclusively on human-defined knowledge concepts (KCs) associated with exercises. As a result, the effectiveness of these models is highly dependent on the quality and completeness of the predefined KCs. Human errors in labeling and the cost of covering all potential underlying KCs can limit model performance. In this paper, we propose a KT model, Sparse Binary Representation KT (SBRKT), that generates new KC labels, referred to as auxiliary KCs, which can augment the predefined KCs to address the limitations of relying solely on human-defined KCs. These are learned through a binary vector representation, where each bit indicates the presence (one) or absence (zero) of an auxiliary KC. The resulting discrete representation allows these auxiliary KCs to be utilized in training any KT model that incorporates KCs. Unlike pre-trained dense embeddings, which are limited to models designed to accept such vectors, our discrete representations are compatible with both classical models, such as Bayesian Knowledge Tracing (BKT), and modern deep learning approaches. To generate this discrete representation, SBRKT employs a binarization method that learns a sparse representation, fully trainable via stochastic gradient descent. Additionally, SBRKT incorporates a recurrent neural network (RNN) to capture temporal dynamics and predict future student responses by effectively combining the auxiliary and predefined KCs. Experimental results demonstrate that SBRKT outperforms the tested baselines on several datasets and achieves competitive performance on others. Furthermore, incorporating the learned auxiliary KCs consistently enhances the performance of BKT across all tested datasets.

arXiv:2501.07903공식 코드 · Papers with Code

Optimal Classification Trees for Continuous Feature Data Using Dynamic Programming with Branch-and-Bound

Computing an optimal classification tree that provably maximizes training performance within a given size limit, is NP-hard, and in practice, most state-of-the-art methods do not scale beyond computing optimal trees of depth three. Therefore, most methods rely on a coarse binarization of continuous features to maintain scalability. We propose a novel algorithm that optimizes trees directly on the continuous feature data using dynamic programming with branch-and-bound. We develop new pruning techniques that eliminate many sub-optimal splits in the search when similar to previously computed splits and we provide an efficient subroutine for computing optimal depth-two trees. Our experiments demonstrate that these techniques improve runtime by one or more orders of magnitude over state-of-the-art optimal methods and improve test accuracy by 5% over greedy heuristics.

arXiv:2501.05904

Binary Event-Driven Spiking Transformer

Transformer-based Spiking Neural Networks (SNNs) introduce a novel event-driven self-attention paradigm that combines the high performance of Transformers with the energy efficiency of SNNs. However, the larger model size and increased computational demands of the Transformer structure limit their practicality in resource-constrained scenarios. In this paper, we integrate binarization techniques into Transformer-based SNNs and propose the Binary Event-Driven Spiking Transformer, i.e. BESTformer. The proposed BESTformer can significantly reduce storage and computational demands by representing weights and attention maps with a mere 1-bit. However, BESTformer suffers from a severe performance drop from its full-precision counterpart due to the limited representation capability of binarization. To address this issue, we propose a Coupled Information Enhancement (CIE) method, which consists of a reversible framework and information enhancement distillation. By maximizing the mutual information between the binary model and its full-precision counterpart, the CIE method effectively mitigates the performance degradation of the BESTformer. Extensive experiments on static and neuromorphic datasets demonstrate that our method achieves superior performance to other binary SNNs, showcasing its potential as a compact yet high-performance model for resource-limited edge devices.

arXiv:2501.00741

Towards End-to-End Neuromorphic Voxel-based 3D Object Reconstruction Without Physical Priors

Neuromorphic cameras, also known as event cameras, are asynchronous brightness-change sensors that can capture extremely fast motion without suffering from motion blur, making them particularly promising for 3D reconstruction in extreme environments. However, existing research on 3D reconstruction using monocular neuromorphic cameras is limited, and most of the methods rely on estimating physical priors and employ complex multi-step pipelines. In this work, we propose an end-to-end method for dense voxel 3D reconstruction using neuromorphic cameras that eliminates the need to estimate physical priors. Our method incorporates a novel event representation to enhance edge features, enabling the proposed feature-enhancement model to learn more effectively. Additionally, we introduced Optimal Binarization Threshold Selection Principle as a guideline for future related work, using the optimal reconstruction results achieved with threshold optimization as the benchmark. Our method achieves a 54.6% improvement in reconstruction accuracy compared to the baseline method.

arXiv:2412.16449

CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference

Binarized Neural Networks (BNN) offer efficient implementations for machine learning tasks and facilitate Privacy-Preserving Machine Learning (PPML) by simplifying operations with binary values. Nevertheless, challenges persist in terms of communication and accuracy in their application scenarios. In this work, we introduce CBNN, a three-party secure computation framework tailored for efficient BNN inference. Leveraging knowledge distillation and separable convolutions, CBNN transforms standard BNNs into MPC-friendly customized BNNs, maintaining high utility. It performs secure inference using optimized protocols for basic operations. Specifically, CBNN enhances linear operations with replicated secret sharing and MPC-friendly convolutions, while introducing a novel secure activation function to optimize non-linear operations. We demonstrate the effectiveness of CBNN by transforming and securely implementing several typical BNN models. Experimental results indicate that CBNN maintains impressive performance even after customized binarization and security measures

arXiv:2412.11634공식 코드 · Papers with Code

Predicting the Original Appearance of Damaged Historical Documents

Historical documents encompass a wealth of cultural treasures but suffer from severe damages including character missing, paper damage, and ink erosion over time. However, existing document processing methods primarily focus on binarization, enhancement, etc., neglecting the repair of these damages. To this end, we present a new task, termed Historical Document Repair (HDR), which aims to predict the original appearance of damaged historical documents. To fill the gap in this field, we propose a large-scale dataset HDR28K and a diffusion-based network DiffHDR for historical document repair. Specifically, HDR28K contains 28,552 damaged-repaired image pairs with character-level annotations and multi-style degradations. Moreover, DiffHDR augments the vanilla diffusion framework with semantic and spatial information and a meticulously designed character perceptual loss for contextual and visual coherence. Experimental results demonstrate that the proposed DiffHDR trained using HDR28K significantly surpasses existing approaches and exhibits remarkable performance in handling real damaged documents. Notably, DiffHDR can also be extended to document editing and text block generation, showcasing its high flexibility and generalization capacity. We believe this study could pioneer a new direction of document processing and contribute to the inheritance of invaluable cultures and civilizations. The dataset and code is available at https://github.com/yeungchenwa/HDR.

arXiv:2412.05926공식 코드 · Papers with Code

BiDM: Pushing the Limit of Quantization for Diffusion Models

Diffusion models (DMs) have been significantly developed and widely used in various applications due to their excellent generative qualities. However, the expensive computation and massive parameters of DMs hinder their practical use in resource-constrained scenarios. As one of the effective compression approaches, quantization allows DMs to achieve storage saving and inference acceleration by reducing bit-width while maintaining generation performance. However, as the most extreme quantization form, 1-bit binarization causes the generation performance of DMs to face severe degradation or even collapse. This paper proposes a novel method, namely BiDM, for fully binarizing weights and activations of DMs, pushing quantization to the 1-bit limit. From a temporal perspective, we introduce the Timestep-friendly Binary Structure (TBS), which uses learnable activation binarizers and cross-timestep feature connections to address the highly timestep-correlated activation features of DMs. From a spatial perspective, we propose Space Patched Distillation (SPD) to address the difficulty of matching binary features during distillation, focusing on the spatial locality of image generation tasks and noise estimation networks. As the first work to fully binarize DMs, the W1A1 BiDM on the LDM-4 model for LSUN-Bedrooms 256$\times$256 achieves a remarkable FID of 22.74, significantly outperforming the current state-of-the-art general binarization methods with an FID of 59.44 and invalid generative samples, and achieves up to excellent 28.0 times storage and 52.7 times OPs savings. The code is available at https://github.com/Xingyu-Zheng/BiDM .

arXiv:2412.05225

BEExformer: A Fast Inferencing Transformer Architecture via Binarization with Multiple Early Exits

Large Language Models (LLMs) based on transformers achieve cutting-edge results on a variety of applications. However, their enormous size and processing requirements make deployment on devices with constrained resources extremely difficult. Among various efficiency considerations, model binarization and Early Exit (EE) are common effective solutions. However, binarization may lead to performance loss due to reduced precision affecting gradient estimation and parameter updates. Besides, the present early-exit mechanisms are still in the nascent stages of research. To ameliorate these issues, we propose Binarized Early Exit Transformer (BEExformer), the first-ever selective learning transformer architecture to combine early exit with binarization for textual inference. It improves the binarization process through a differentiable second-order approximation to the impulse function. This enables gradient computation concerning both the sign as well as the magnitude of the weights. In contrast to absolute threshold-based EE, the proposed EE mechanism hinges on fractional reduction in entropy among intermediate transformer blocks with soft-routing loss estimation. While binarization results in 18.44 times reduction in model size, early exit reduces the FLOPs during inference by 54.85% and even improves accuracy by 5.98% through resolving the "overthinking" problem inherent in deep networks. Moreover, the proposed BEExformer simplifies training by not requiring knowledge distillation from a full-precision LLM. Extensive evaluation on the GLUE dataset and comparison with the SOTA works showcase its pareto-optimal performance-efficiency trade-off.

arXiv:2412.04137

Text Change Detection in Multilingual Documents Using Image Comparison

Document comparison typically relies on optical character recognition (OCR) as its core technology. However, OCR requires the selection of appropriate language models for each document and the performance of multilingual or hybrid models remains limited. To overcome these challenges, we propose text change detection (TCD) using an image comparison model tailored for multilingual documents. Unlike OCR-based approaches, our method employs word-level text image-to-image comparison to detect changes. Our model generates bidirectional change segmentation maps between the source and target documents. To enhance performance without requiring explicit text alignment or scaling preprocessing, we employ correlations among multi-scale attention features. We also construct a benchmark dataset comprising actual printed and scanned word pairs in various languages to evaluate our model. We validate our approach using our benchmark dataset and public benchmarks Distorted Document Images and the LRDE Document Binarization Dataset. We compare our model against state-of-the-art semantic segmentation and change detection models, as well as to conventional OCR-based models.

arXiv:2412.01601

Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection

The problem of converting images of text into plain text is a widely researched topic in both academia and industry. Arabic handwritten Text Recognation (AHTR) poses additional challenges due to diverse handwriting styles and limited labeled data. In this paper we present a complete OCR pipeline that starts with line segmentation using Differentiable Binarization and Adaptive Scale Fusion techniques to ensure accurate detection of text lines. Following segmentation, a CNN-BiLSTM-CTC architecture is applied to recognize characters. Our system, trained on the Arabic Multi-Fonts Dataset (AMFDS), achieves a Character Recognition Rate (CRR) of 99.20% and a Word Recognition Rate (WRR) of 93.75% on single-word samples containing 7 to 10 characters, along with a CRR of 83.76% for sentences. These results demonstrate the system's strong performance in handling Arabic scripts, establishing a new benchmark for AHTR systems.

arXiv:2411.10668

Segmentation of Ink and Parchment in Dead Sea Scroll Fragments

The discovery of the Dead Sea Scrolls over 60 years ago is widely regarded as one of the greatest archaeological breakthroughs in modern history. Recent study of the scrolls presents ongoing computational challenges, including determining the provenance of fragments, clustering fragments based on their degree of similarity, and pairing fragments that originate from the same manuscript -- all tasks that require focusing on individual letter and fragment shapes. This paper presents a computational method for segmenting ink and parchment regions in multispectral images of Dead Sea Scroll fragments. Using the newly developed Qumran Segmentation Dataset (QSD) consisting of 20 fragments, we apply multispectral thresholding to isolate ink and parchment regions based on their unique spectral signatures. To refine segmentation accuracy, we introduce an energy minimization technique that leverages ink contours, which are more distinguishable from the background and less noisy than inner ink regions. Experimental results demonstrate that this Multispectral Thresholding and Energy Minimization (MTEM) method achieves significant improvements over traditional binarization approaches like Otsu and Sauvola in parchment segmentation and is successful at delineating ink borders, in distinction from holes and background regions.

arXiv:2411.11843

Bi-Mamba: Towards Accurate 1-Bit State Space Models

The typical selective state-space model (SSM) of Mamba addresses several limitations of Transformers, such as quadratic computational complexity with sequence length and significant inference-time memory requirements due to the key-value cache. However, the growing size of Mamba models continues to pose training and deployment challenges and raises environmental concerns due to considerable energy consumption. In this work, we introduce Bi-Mamba, a scalable and powerful 1-bit Mamba architecture designed for more efficient large language models with multiple sizes across 780M, 1.3B, and 2.7B. Bi-Mamba models are trained from scratch on data volume as regular LLM pertaining using an autoregressive distillation loss. Extensive experimental results on language modeling demonstrate that Bi-Mamba achieves performance comparable to its full-precision counterparts (e.g., FP16 or BF16) and much better accuracy than post-training-binarization (PTB) Mamba baselines, while significantly reducing memory footprint and energy consumption compared to the original Mamba model. Our study pioneers a new linear computational complexity LLM framework under low-bit representation and facilitates the future design of specialized hardware tailored for efficient 1-bit Mamba-based LLMs.

arXiv:2411.10346공식 코드 · Papers with Code

BiDense: Binarization for Dense Prediction

Dense prediction is a critical task in computer vision. However, previous methods often require extensive computational resources, which hinders their real-world application. In this paper, we propose BiDense, a generalized binary neural network (BNN) designed for efficient and accurate dense prediction tasks. BiDense incorporates two key techniques: the Distribution-adaptive Binarizer (DAB) and the Channel-adaptive Full-precision Bypass (CFB). The DAB adaptively calculates thresholds and scaling factors for binarization, effectively retaining more information within BNNs. Meanwhile, the CFB facilitates full-precision bypassing for binary convolutional layers undergoing various channel size transformations, which enhances the propagation of real-valued signals and minimizes information loss. By leveraging these techniques, BiDense preserves more real-valued information, enabling more accurate and detailed dense predictions in BNNs. Extensive experiments demonstrate that our framework achieves performance levels comparable to full-precision models while significantly reducing memory usage and computational costs.

arXiv:2411.06359

Evaluating tDCS Intervention Effectiveness via Functional Connectivity Network on Resting-State EEG Data in Major Depressive Disorder

Transcranial direct current stimulation (tDCS) has emerged as a promising non-invasive therapeutic intervention for major depressive disorder (MDD), yet its effects on neural mechanisms remain incompletely understood. This study investigates the impact of tDCS in individuals with MDD using resting-state EEG data and network neuroscience to analyze functional connectivity. We examined power spectral density (PSD) changes and functional connectivity (FC) patterns across theta, alpha, and beta bands before and after tDCS intervention. A notable aspect of this research involves the modification of the binarizing threshold algorithm to assess functional connectivity networks, facilitating a meaningful comparison at the group level. Our analysis using optimal threshold binarization techniques revealed significant modifications in network topology, particularly evident in the beta band, indicative of reduced randomization or enhanced small-worldness after tDCS. Furthermore, the hubness analysis identified specific brain regions, notably the dorsolateral prefrontal cortex (DLPFC) regions across all frequency bands, exhibiting increased functional connectivity, suggesting their involvement in the antidepressant effects of tDCS. Notably, tDCS intervention transformed the dispersed high connectivity into localized connectivity and increased left-sided asymmetry across all frequency bands. Overall, this study provides valuable insights into the effects of tDCS on neural mechanisms in MDD, offering a potential direction for further research and therapeutic development in the field of neuromodulation for mental health disorders.

arXiv:2410.24006공식 코드 · Papers with Code

DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination

In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems. Although diffusion models have shown remarkable capacity in image synthesis and have been recently utilized to counter $\ell_p$-norm bounded attacks, their potential in mitigating localized patch attacks remains largely underexplored. In this work, we propose DiffPAD, a novel framework that harnesses the power of diffusion models for adversarial patch decontamination. DiffPAD first performs super-resolution restoration on downsampled input images, then adopts binarization, dynamic thresholding scheme and sliding window for effective localization of adversarial patches. Such a design is inspired by the theoretically derived correlation between patch size and diffusion restoration error that is generalized across diverse patch attack scenarios. Finally, DiffPAD applies inpainting techniques to the original input images with the estimated patch region being masked. By integrating closed-form solutions for super-resolution restoration and image inpainting into the conditional reverse sampling process of a pre-trained diffusion model, DiffPAD obviates the need for text guidance or fine-tuning. Through comprehensive experiments, we demonstrate that DiffPAD not only achieves state-of-the-art adversarial robustness against patch attacks but also excels in recovering naturalistic images without patch remnants. The source code is available at https://github.com/JasonFu1998/DiffPAD.

arXiv:2410.14379공식 코드 · Papers with Code

AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios

Recently, multi-class anomaly classification has garnered increasing attention. Previous methods directly cluster anomalies but often struggle due to the lack of anomaly-prior knowledge. Acquiring this knowledge faces two issues: the non-prominent and weak-semantics anomalies. In this paper, we propose AnomalyNCD, a multi-class anomaly classification network compatible with different anomaly detection methods. To address the non-prominence of anomalies, we design main element binarization (MEBin) to obtain anomaly-centered images, ensuring anomalies are learned while avoiding the impact of incorrect detections. Next, to learn anomalies with weak semantics, we design mask-guided representation learning, which focuses on isolated anomalies guided by masks and reduces confusion from erroneous inputs through corrected pseudo labels. Finally, to enable flexible classification at both region and image levels, we develop a region merging strategy that determines the overall image category based on the classified anomaly regions. Our method outperforms the state-of-the-art works on the MVTec AD and MTD datasets. Compared with the current methods, AnomalyNCD combined with zero-shot anomaly detection method achieves a 10.8% $F_1$ gain, 8.8% NMI gain, and 9.5% ARI gain on MVTec AD, and 12.8% $F_1$ gain, 5.7% NMI gain, and 10.8% ARI gain on MTD. Code is available at https://github.com/HUST-SLOW/AnomalyNCD.

arXiv:2410.11553공식 코드 · Papers with Code

Efficiera Residual Networks: Hardware-Friendly Fully Binary Weight with 2-bit Activation Model Achieves Practical ImageNet Accuracy

The edge-device environment imposes severe resource limitations, encompassing computation costs, hardware resource usage, and energy consumption for deploying deep neural network models. Ultra-low-bit quantization and hardware accelerators have been explored as promising approaches to address these challenges. Ultra-low-bit quantization significantly reduces the model size and the computational cost. Despite progress so far, many competitive ultra-low-bit models still partially rely on float or non-ultra-low-bit quantized computation such as the input and output layer. We introduce Efficiera Residual Networks (ERNs), a model optimized for low-resource edge devices. ERNs achieve full ultra-low-bit quantization, with all weights, including the initial and output layers, being binary, and activations set at 2 bits. We introduce the shared constant scaling factor technique to enable integer-valued computation in residual connections, allowing our model to operate without float values until the final convolution layer. Demonstrating competitiveness, ERNs achieve an ImageNet top-1 accuracy of 72.5pt with a ResNet50-compatible architecture and 63.6pt with a model size less than 1MB. Moreover, ERNs exhibit impressive inference times, reaching 300FPS with the smallest model and 60FPS with the largest model on a cost-efficient FPGA device.

arXiv:2410.03129공식 코드 · Papers with Code

ARB-LLM: Alternating Refined Binarizations for Large Language Models

Large Language Models (LLMs) have greatly pushed forward advancements in natural language processing, yet their high memory and computational demands hinder practical deployment. Binarization, as an effective compression technique, can shrink model weights to just 1 bit, significantly reducing the high demands on computation and memory. However, current binarization methods struggle to narrow the distribution gap between binarized and full-precision weights, while also overlooking the column deviation in LLM weight distribution. To tackle these issues, we propose ARB-LLM, a novel 1-bit post-training quantization (PTQ) technique tailored for LLMs. To narrow the distribution shift between binarized and full-precision weights, we first design an alternating refined binarization (ARB) algorithm to progressively update the binarization parameters, which significantly reduces the quantization error. Moreover, considering the pivot role of calibration data and the column deviation in LLM weights, we further extend ARB to ARB-X and ARB-RC. In addition, we refine the weight partition strategy with column-group bitmap (CGB), which further enhance performance. Equipping ARB-X and ARB-RC with CGB, we obtain ARB-LLM$_\text{X}$ and ARB-LLM$_\text{RC}$ respectively, which significantly outperform state-of-the-art (SOTA) binarization methods for LLMs. As a binary PTQ method, our ARB-LLM$_\text{RC}$ is the first to surpass FP16 models of the same size. The code and models will be available at https://github.com/ZHITENGLI/ARB-LLM.

arXiv:2409.11454

Golden Ratio Search: A Low-Power Adversarial Attack for Deep Learning based Modulation Classification

We propose a minimal power white box adversarial attack for Deep Learning based Automatic Modulation Classification (AMC). The proposed attack uses the Golden Ratio Search (GRS) method to find powerful attacks with minimal power. We evaluate the efficacy of the proposed method by comparing it with existing adversarial attack approaches. Additionally, we test the robustness of the proposed attack against various state-of-the-art architectures, including defense mechanisms such as adversarial training, binarization, and ensemble methods. Experimental results demonstrate that the proposed attack is powerful, requires minimal power, and can be generated in less time, significantly challenging the resilience of current AMC methods.