PyTorchKR Papers

최신 논문

총 4,806편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2311.07603공식 코드 · Papers with Code

PECoP: Parameter Efficient Continual Pretraining for Action Quality Assessment

The limited availability of labelled data in Action Quality Assessment (AQA), has forced previous works to fine-tune their models pretrained on large-scale domain-general datasets. This common approach results in weak generalisation, particularly when there is a significant domain shift. We propose a novel, parameter efficient, continual pretraining framework, PECoP, to reduce such domain shift via an additional pretraining stage. In PECoP, we introduce 3D-Adapters, inserted into the pretrained model, to learn spatiotemporal, in-domain information via self-supervised learning where only the adapter modules' parameters are updated. We demonstrate PECoP's ability to enhance the performance of recent state-of-the-art methods (MUSDL, CoRe, and TSA) applied to AQA, leading to considerable improvements on benchmark datasets, JIGSAWS ($\uparrow6.0\%$), MTL-AQA ($\uparrow0.99\%$), and FineDiving ($\uparrow2.54\%$). We also present a new Parkinson's Disease dataset, PD4T, of real patients performing four various actions, where we surpass ($\uparrow3.56\%$) the state-of-the-art in comparison. Our code, pretrained models, and the PD4T dataset are available at https://github.com/Plrbear/PECoP.

arXiv:2311.08359

Rotation-Agnostic Image Representation Learning for Digital Pathology

This paper addresses complex challenges in histopathological image analysis through three key contributions. Firstly, it introduces a fast patch selection method, FPS, for whole-slide image (WSI) analysis, significantly reducing computational cost while maintaining accuracy. Secondly, it presents PathDino, a lightweight histopathology feature extractor with a minimal configuration of five Transformer blocks and only 9 million parameters, markedly fewer than alternatives. Thirdly, it introduces a rotation-agnostic representation learning paradigm using self-supervised learning, effectively mitigating overfitting. We also show that our compact model outperforms existing state-of-the-art histopathology-specific vision transformers on 12 diverse datasets, including both internal datasets spanning four sites (breast, liver, skin, and colorectal) and seven public datasets (PANDA, CAMELYON16, BRACS, DigestPath, Kather, PanNuke, and WSSS4LUAD). Notably, even with a training dataset of 6 million histopathology patches from The Cancer Genome Atlas (TCGA), our approach demonstrates an average 8.5% improvement in patch-level majority vote performance. These contributions provide a robust framework for enhancing image analysis in digital pathology, rigorously validated through extensive evaluation. Project Page: https://kimialabmayo.github.io/PathDino-Page/

arXiv:2311.06712공식 코드 · Papers with Code

PuzzleTuning: Explicitly Bridge Pathological and Natural Image with Puzzles

Pathological image analysis is a crucial field in computer vision. Due to the annotation scarcity in the pathological field, pre-training with self-supervised learning (SSL) is widely applied to learn on unlabeled images. However, the current SSL-based pathological pre-training: (1) does not explicitly explore the essential focuses of the pathological field, and (2) does not effectively bridge with and thus take advantage of the knowledge from natural images. To explicitly address them, we propose our large-scale PuzzleTuning framework, containing the following innovations. Firstly, we define three task focuses that can effectively bridge knowledge of pathological and natural domain: appearance consistency, spatial consistency, and restoration understanding. Secondly, we devise a novel multiple puzzle restoring task, which explicitly pre-trains the model regarding these focuses. Thirdly, we introduce an explicit prompt-tuning process to incrementally integrate the domain-specific knowledge. It builds a bridge to align the large domain gap between natural and pathological images. Additionally, a curriculum-learning training strategy is designed to regulate task difficulty, making the model adaptive to the puzzle restoring complexity. Experimental results show that our PuzzleTuning framework outperforms the previous state-of-the-art methods in various downstream tasks on multiple datasets. The code, demo, and pre-trained weights are available at https://github.com/sagizty/PuzzleTuning.

arXiv:2311.07093

On the Effectiveness of ASR Representations in Real-world Noisy Speech Emotion Recognition

This paper proposes an efficient attempt to noisy speech emotion recognition (NSER). Conventional NSER approaches have proven effective in mitigating the impact of artificial noise sources, such as white Gaussian noise, but are limited to non-stationary noises in real-world environments due to their complexity and uncertainty. To overcome this limitation, we introduce a new method for NSER by adopting the automatic speech recognition (ASR) model as a noise-robust feature extractor to eliminate non-vocal information in noisy speech. We first obtain intermediate layer information from the ASR model as a feature representation for emotional speech and then apply this representation for the downstream NSER task. Our experimental results show that 1) the proposed method achieves better NSER performance compared with the conventional noise reduction method, 2) outperforms self-supervised learning approaches, and 3) even outperforms text-based approaches using ASR transcription or the ground truth transcription of noisy speech.

arXiv:2311.06834

Osteoporosis Prediction from Hand and Wrist X-rays using Image Segmentation and Self-Supervised Learning

Osteoporosis is a widespread and chronic metabolic bone disease that often remains undiagnosed and untreated due to limited access to bone mineral density (BMD) tests like Dual-energy X-ray absorptiometry (DXA). In response to this challenge, current advancements are pivoting towards detecting osteoporosis by examining alternative indicators from peripheral bone areas, with the goal of increasing screening rates without added expenses or time. In this paper, we present a method to predict osteoporosis using hand and wrist X-ray images, which are both widely accessible and affordable, though their link to DXA-based data is not thoroughly explored. Initially, our method segments the ulnar, radius, and metacarpal bones using a foundational model for image segmentation. Then, we use a self-supervised learning approach to extract meaningful representations without the need for explicit labels, and move on to classify osteoporosis in a supervised manner. Our method is evaluated on a dataset with 192 individuals, cross-referencing their verified osteoporosis conditions against the standard DXA test. With a notable classification score (AUC=0.83), our model represents a pioneering effort in leveraging vision-based techniques for osteoporosis identification from the peripheral skeleton sites.

arXiv:2311.06504공식 코드 · Papers with Code

SCL-VI: Self-supervised Context Learning for Visual Inspection of Industrial Defects

The unsupervised visual inspection of defects in industrial products poses a significant challenge due to substantial variations in product surfaces. Current unsupervised models struggle to strike a balance between detecting texture and object defects, lacking the capacity to discern latent representations and intricate features. In this paper, we present a novel self-supervised learning algorithm designed to derive an optimal encoder by tackling the renowned jigsaw puzzle. Our approach involves dividing the target image into nine patches, tasking the encoder with predicting the relative position relationships between any two patches to extract rich semantics. Subsequently, we introduce an affinity-augmentation method to accentuate differences between normal and abnormal latent representations. Leveraging the classic support vector data description algorithm yields final detection results. Experimental outcomes demonstrate that our proposed method achieves outstanding detection and segmentation performance on the widely used MVTec AD dataset, with rates of 95.8% and 96.8%, respectively, establishing a state-of-the-art benchmark for both texture and object defects. Comprehensive experimentation underscores the effectiveness of our approach in diverse industrial applications.

arXiv:2311.06691

Automatized Self-Supervised Learning for Skin Lesion Screening

Melanoma, the deadliest form of skin cancer, has seen a steady increase in incidence rates worldwide, posing a significant challenge to dermatologists. Early detection is crucial for improving patient survival rates. However, performing total body screening (TBS), i.e., identifying suspicious lesions or ugly ducklings (UDs) by visual inspection, can be challenging and often requires sound expertise in pigmented lesions. To assist users of varying expertise levels, an artificial intelligence (AI) decision support tool was developed. Our solution identifies and characterizes UDs from real-world wide-field patient images. It employs a state-of-the-art object detection algorithm to locate and isolate all skin lesions present in a patient's total body images. These lesions are then sorted based on their level of suspiciousness using a self-supervised AI approach, tailored to the specific context of the patient under examination. A clinical validation study was conducted to evaluate the tool's performance. The results demonstrated an average sensitivity of 95% for the top-10 AI-identified UDs on skin lesions selected by the majority of experts in pigmented skin lesions. The study also found that the tool increased dermatologists' confidence when formulating a diagnosis, and the average majority agreement with the top-10 AI-identified UDs reached 100% when assisted by our tool. With the development of this AI-based decision support tool, we aim to address the shortage of specialists, enable faster consultation times for patients, and demonstrate the impact and usability of AI-assisted screening. Future developments will include expanding the dataset to include histologically confirmed melanoma and validating the tool for additional body regions.

arXiv:2311.05565공식 코드 · Papers with Code

High-Performance Transformers for Table Structure Recognition Need Early Convolutions

Table structure recognition (TSR) aims to convert tabular images into a machine-readable format, where a visual encoder extracts image features and a textual decoder generates table-representing tokens. Existing approaches use classic convolutional neural network (CNN) backbones for the visual encoder and transformers for the textual decoder. However, this hybrid CNN-Transformer architecture introduces a complex visual encoder that accounts for nearly half of the total model parameters, markedly reduces both training and inference speed, and hinders the potential for self-supervised learning in TSR. In this work, we design a lightweight visual encoder for TSR without sacrificing expressive power. We discover that a convolutional stem can match classic CNN backbone performance, with a much simpler model. The convolutional stem strikes an optimal balance between two crucial factors for high-performance TSR: a higher receptive field (RF) ratio and a longer sequence length. This allows it to "see" an appropriate portion of the table and "store" the complex table structure within sufficient context length for the subsequent transformer. We conducted reproducible ablation studies and open-sourced our code at https://github.com/poloclub/tsr-convstem to enhance transparency, inspire innovations, and facilitate fair comparisons in our domain as tables are a promising modality for representation learning.

arXiv:2311.04847

Are foundation models efficient for medical image segmentation?

Foundation models are experiencing a surge in popularity. The Segment Anything model (SAM) asserts an ability to segment a wide spectrum of objects but required supervised training at unprecedented scale. We compared SAM's performance (against clinical ground truth) and resources (labeling time, compute) to a modality-specific, label-free self-supervised learning (SSL) method on 25 measurements for 100 cardiac ultrasounds. SAM performed poorly and required significantly more labeling and computing resources, demonstrating worse efficiency than SSL.

arXiv:2311.04834공식 코드 · Papers with Code

Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction

We present a novel self-supervised approach for representation learning, particularly for the task of Visual Relationship Detection (VRD). Motivated by the effectiveness of Masked Image Modeling (MIM), we propose Masked Bounding Box Reconstruction (MBBR), a variation of MIM where a percentage of the entities/objects within a scene are masked and subsequently reconstructed based on the unmasked objects. The core idea is that, through object-level masked modeling, the network learns context-aware representations that capture the interaction of objects within a scene and thus are highly predictive of visual object relationships. We extensively evaluate learned representations, both qualitatively and quantitatively, in a few-shot setting and demonstrate the efficacy of MBBR for learning robust visual representations, particularly tailored for VRD. The proposed method is able to surpass state-of-the-art VRD methods on the Predicate Detection (PredDet) evaluation setting, using only a few annotated samples. We make our code available at https://github.com/deeplab-ai/SelfSupervisedVRD.

arXiv:2311.04442공식 코드 · Papers with Code

SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification

Masked image modeling (MIM) is a highly popular and effective self-supervised learning method for image understanding. Existing MIM-based methods mostly focus on spatial feature modeling, neglecting spectral feature modeling. Meanwhile, existing MIM-based methods use Transformer for feature extraction, some local or high-frequency information may get lost. To this end, we propose a spatial-spectral masked auto-encoder (SS-MAE) for HSI and LiDAR/SAR data joint classification. Specifically, SS-MAE consists of a spatial-wise branch and a spectral-wise branch. The spatial-wise branch masks random patches and reconstructs missing pixels, while the spectral-wise branch masks random spectral channels and reconstructs missing channels. Our SS-MAE fully exploits the spatial and spectral representations of the input data. Furthermore, to complement local features in the training stage, we add two lightweight CNNs for feature extraction. Both global and local features are taken into account for feature modeling. To demonstrate the effectiveness of the proposed SS-MAE, we conduct extensive experiments on three publicly available datasets. Extensive experiments on three multi-source datasets verify the superiority of our SS-MAE compared with several state-of-the-art baselines. The source codes are available at \url{https://github.com/summitgao/SS-MAE}.

arXiv:2311.03650

Image Generation and Learning Strategy for Deep Document Forgery Detection

In recent years, document processing has flourished and brought numerous benefits. However, there has been a significant rise in reported cases of forged document images. Specifically, recent advancements in deep neural network (DNN) methods for generative tasks may amplify the threat of document forgery. Traditional approaches for forged document images created by prevalent copy-move methods are unsuitable against those created by DNN-based methods, as we have verified. To address this issue, we construct a training dataset of document forgery images, named FD-VIED, by emulating possible attacks, such as text addition, removal, and replacement with recent DNN-methods. Additionally, we introduce an effective pre-training approach through self-supervised learning with both natural images and document images. In our experiments, we demonstrate that our approach enhances detection performance.

arXiv:2311.03402

CycleCL: Self-supervised Learning for Periodic Videos

Analyzing periodic video sequences is a key topic in applications such as automatic production systems, remote sensing, medical applications, or physical training. An example is counting repetitions of a physical exercise. Due to the distinct characteristics of periodic data, self-supervised methods designed for standard image datasets do not capture changes relevant to the progression of the cycle and fail to ignore unrelated noise. They thus do not work well on periodic data. In this paper, we propose CycleCL, a self-supervised learning method specifically designed to work with periodic data. We start from the insight that a good visual representation for periodic data should be sensitive to the phase of a cycle, but be invariant to the exact repetition, i.e. it should generate identical representations for a specific phase throughout all repetitions. We exploit the repetitions in videos to design a novel contrastive learning method based on a triplet loss that optimizes for these desired properties. Our method uses pre-trained features to sample pairs of frames from approximately the same phase and negative pairs of frames from different phases. Then, we iterate between optimizing a feature encoder and resampling triplets, until convergence. By optimizing a model this way, we are able to learn features that have the mentioned desired properties. We evaluate CycleCL on an industrial and multiple human actions datasets, where it significantly outperforms previous video-based self-supervised learning methods on all tasks.

arXiv:2311.03386공식 코드 · Papers with Code

A Simple and Efficient Baseline for Data Attribution on Images

Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs during deployment. However, current state-of-the-art approaches require a large ensemble of as many as 300,000 models to accurately attribute model predictions. These approaches therefore come at a high computational cost, are memory intensive, and are hard to scale to large models or datasets. In this work, we focus on a minimalist baseline, utilizing the feature space of a backbone pretrained via self-supervised learning to perform data attribution. Our method is model-agnostic and scales easily to large datasets. We show results on CIFAR-10 and ImageNet, achieving strong performance that rivals or outperforms state-of-the-art approaches at a fraction of the compute or memory cost. Contrary to prior work, our results reinforce the intuition that a model's prediction on one image is most impacted by visually similar training samples. Our approach serves as a simple and efficient baseline for data attribution on images.

arXiv:2311.04069공식 코드 · Papers with Code

LISBET: a machine learning model for the automatic segmentation of social behavior motifs

Social behavior is crucial for survival in many animal species, and a heavily investigated research subject. Current analysis methods generally rely on measuring animal interaction time or annotating predefined behaviors. However, these approaches are time consuming, human biased, and can fail to capture subtle behaviors. Here we introduce LISBET (LISBET Is a Social BEhavior Transformer), a machine learning model for detecting and segmenting social interactions. Using self-supervised learning on body tracking data, our model eliminates the need for extensive human annotation. We tested LISBET in three scenarios across multiple datasets in mice: supervised behavior classification, unsupervised motifs segmentation, and unsupervised animal phenotyping. Additionally, in vivo electrophysiology revealed distinct neural signatures in the Ventral Tegmental Area corresponding to motifs identified by our model. In summary, LISBET automates data annotation and reduces human bias in social behavior research, offering a promising approach to enhance our understanding of behavior and its neural correlates.

arXiv:2311.03785

Self-MI: Efficient Multimodal Fusion via Self-Supervised Multi-Task Learning with Auxiliary Mutual Information Maximization

Multimodal representation learning poses significant challenges in capturing informative and distinct features from multiple modalities. Existing methods often struggle to exploit the unique characteristics of each modality due to unified multimodal annotations. In this study, we propose Self-MI in the self-supervised learning fashion, which also leverage Contrastive Predictive Coding (CPC) as an auxiliary technique to maximize the Mutual Information (MI) between unimodal input pairs and the multimodal fusion result with unimodal inputs. Moreover, we design a label generation module, $ULG_{MI}$ for short, that enables us to create meaningful and informative labels for each modality in a self-supervised manner. By maximizing the Mutual Information, we encourage better alignment between the multimodal fusion and the individual modalities, facilitating improved multimodal fusion. Extensive experiments on three benchmark datasets including CMU-MOSI, CMU-MOSEI, and SIMS, demonstrate the effectiveness of Self-MI in enhancing the multimodal fusion task.

arXiv:2311.04215

Wearable data from subjects playing Super Mario, sitting university exams, or performing physical exercise help detect acute mood episodes via self-supervised learning

Personal sensing, leveraging data passively and near-continuously collected with wearables from patients in their ecological environment, is a promising paradigm to monitor mood disorders (MDs), a major determinant of worldwide disease burden. However, collecting and annotating wearable data is very resource-intensive. Studies of this kind can thus typically afford to recruit only a couple dozens of patients. This constitutes one of the major obstacles to applying modern supervised machine learning techniques to MDs detection. In this paper, we overcome this data bottleneck and advance the detection of MDs acute episode vs stable state from wearables data on the back of recent advances in self-supervised learning (SSL). This leverages unlabelled data to learn representations during pre-training, subsequently exploited for a supervised task. First, we collected open-access datasets recording with an Empatica E4 spanning different, unrelated to MD monitoring, personal sensing tasks -- from emotion recognition in Super Mario players to stress detection in undergraduates -- and devised a pre-processing pipeline performing on-/off-body detection, sleep-wake detection, segmentation, and (optionally) feature extraction. With 161 E4-recorded subjects, we introduce E4SelfLearning, the largest to date open access collection, and its pre-processing pipeline. Second, we show that SSL confidently outperforms fully-supervised pipelines using either our novel E4-tailored Transformer architecture (E4mer) or classical baseline XGBoost: 81.23% against 75.35% (E4mer) and 72.02% (XGBoost) correctly classified recording segments from 64 (half acute, half stable) patients. Lastly, we illustrate that SSL performance is strongly associated with the specific surrogate task employed for pre-training as well as with unlabelled data availability.

arXiv:2311.03768

PT-Tuning: Bridging the Gap between Time Series Masked Reconstruction and Forecasting via Prompt Token Tuning

Self-supervised learning has been actively studied in time series domain recently, especially for masked reconstruction. Most of these methods follow the "Pre-training + Fine-tuning" paradigm in which a new decoder replaces the pre-trained decoder to fit for a specific downstream task, leading to inconsistency of upstream and downstream tasks. In this paper, we first point out that the unification of task objectives and adaptation for task difficulty are critical for bridging the gap between time series masked reconstruction and forecasting. By reserving the pre-trained mask token during fine-tuning stage, the forecasting task can be taken as a special case of masked reconstruction, where the future values are masked and reconstructed based on history values. It guarantees the consistency of task objectives but there is still a gap in task difficulty. Because masked reconstruction can utilize contextual information while forecasting can only use historical information to reconstruct. To further mitigate the existed gap, we propose a simple yet effective prompt token tuning (PT-Tuning) paradigm, in which all pre-trained parameters are frozen and only a few trainable prompt tokens are added to extended mask tokens in element-wise manner. Extensive experiments on real-world datasets demonstrate the superiority of our proposed paradigm with state-of-the-art performance compared to representation learning and end-to-end supervised forecasting methods.

arXiv:2311.03318공식 코드 · Papers with Code

A Foundation Model for Music Informatics

This paper investigates foundation models tailored for music informatics, a domain currently challenged by the scarcity of labeled data and generalization issues. To this end, we conduct an in-depth comparative study among various foundation model variants, examining key determinants such as model architectures, tokenization methods, temporal resolution, data, and model scalability. This research aims to bridge the existing knowledge gap by elucidating how these individual factors contribute to the success of foundation models in music informatics. Employing a careful evaluation framework, we assess the performance of these models across diverse downstream tasks in music information retrieval, with a particular focus on token-level and sequence-level classification. Our results reveal that our model demonstrates robust performance, surpassing existing models in specific key metrics. These findings contribute to the understanding of self-supervised learning in music informatics and pave the way for developing more effective and versatile foundation models in the field. A pretrained version of our model is publicly available to foster reproducibility and future research.

arXiv:2311.02316

Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells

To solve the spatial problems of mapping, localization and navigation, the mammalian lineage has developed striking spatial representations. One important spatial representation is the Nobel-prize winning grid cells: neurons that represent self-location, a local and aperiodic quantity, with seemingly bizarre non-local and spatially periodic activity patterns of a few discrete periods. Why has the mammalian lineage learnt this peculiar grid representation? Mathematical analysis suggests that this multi-periodic representation has excellent properties as an algebraic code with high capacity and intrinsic error-correction, but to date, there is no satisfactory synthesis of core principles that lead to multi-modular grid cells in deep recurrent neural networks. In this work, we begin by identifying key insights from four families of approaches to answering the grid cell question: coding theory, dynamical systems, function optimization and supervised deep learning. We then leverage our insights to propose a new approach that combines the strengths of all four approaches. Our approach is a self-supervised learning (SSL) framework - including data, data augmentations, loss functions and a network architecture - motivated from a normative perspective, without access to supervised position information or engineering of particular readout representations as needed in previous approaches. We show that multiple grid cell modules can emerge in networks trained on our SSL framework and that the networks and emergent representations generalize well outside their training distribution. This work contains insights for neuroscientists interested in the origins of grid cells as well as machine learning researchers interested in novel SSL frameworks.