PyTorchKR Papers

최신 논문

총 10,566편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2305.08551

Enhancing Performance of Vision Transformers on Small Datasets through Local Inductive Bias Incorporation

Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) when trained from scratch on smaller datasets, possibly due to a lack of local inductive bias in the architecture. Recent studies have therefore added locality to the architecture and demonstrated that it can help ViTs achieve performance comparable to CNNs in the small-size dataset regime. Existing methods, however, are architecture-specific or have higher computational and memory costs. Thus, we propose a module called Local InFormation Enhancer (LIFE) that extracts patch-level local information and incorporates it into the embeddings used in the self-attention block of ViTs. Our proposed module is memory and computation efficient, as well as flexible enough to process auxiliary tokens such as the classification and distillation tokens. Empirical results show that the addition of the LIFE module improves the performance of ViTs on small image classification datasets. We further demonstrate how the effect can be extended to downstream tasks, such as object detection and semantic segmentation. In addition, we introduce a new visualization method, Dense Attention Roll-Out, specifically designed for dense prediction tasks, allowing the generation of class-specific attention maps utilizing the attention maps of all tokens.

arXiv:2305.07598공식 코드 · Papers with Code

Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer

Detection Transformers (DETR) have recently set new benchmarks in object detection. However, their performance in detecting rotated objects lags behind established oriented object detectors. Our analysis identifies a key observation: the boundary discontinuity and square-like problem in bipartite matching poses an issue with assigning appropriate ground truths to predictions, leading to duplicate low-confidence predictions. To address this, we introduce a Hausdorff distance-based cost for bipartite matching, which more accurately quantifies the discrepancy between predictions and ground truths. Additionally, we find that a static denoising approach impedes the training of rotated DETR, especially as the quality of the detector's predictions begins to exceed that of the noised ground truths. To overcome this, we propose an adaptive query denoising method that employs bipartite matching to selectively eliminate noised queries that detract from model improvement. When compared to models adopting a ResNet-50 backbone, our proposed model yields remarkable improvements, achieving $\textbf{+4.18}$ AP$_{50}$, $\textbf{+4.59}$ AP$_{50}$, and $\textbf{+4.99}$ AP$_{50}$ on DOTA-v2.0, DOTA-v1.5, and DIOR-R, respectively.

arXiv:2305.07270공식 코드 · Papers with Code

SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detection

Transformer-based methods have demonstrated superior performance for monocular 3D object detection recently, which aims at predicting 3D attributes from a single 2D image. Most existing transformer-based methods leverage both visual and depth representations to explore valuable query points on objects, and the quality of the learned query points has a great impact on detection accuracy. Unfortunately, existing unsupervised attention mechanisms in transformers are prone to generate low-quality query features due to inaccurate receptive fields, especially on hard objects. To tackle this problem, this paper proposes a novel "Supervised Scale-aware Deformable Attention" (SSDA) for monocular 3D object detection. Specifically, SSDA presets several masks with different scales and utilizes depth and visual features to adaptively learn a scale-aware filter for object query augmentation. Imposing the scale awareness, SSDA could well predict the accurate receptive field of an object query to support robust query feature generation. Aside from this, SSDA is assigned with a Weighted Scale Matching (WSM) loss to supervise scale prediction, which presents more confident results as compared to the unsupervised attention mechanisms. Extensive experiments on the KITTI and Waymo Open datasets demonstrate that SSDA significantly improves the detection accuracy, especially on moderate and hard objects, yielding state-of-the-art performance as compared to the existing approaches. Our code will be made publicly available at https://github.com/mikasa3lili/SSD-MonoDETR.

arXiv:2305.07552

Dish detection in food platters: A framework for automated diet logging and nutrition management

Diet is central to the epidemic of lifestyle disorders. Accurate and effortless diet logging is one of the significant bottlenecks for effective diet management and calorie restriction. Dish detection from food platters is a challenging problem due to a visually complex food layout. We present an end-to-end computational framework for diet management, from data compilation, annotation, and state-of-the-art model identification to its mobile app implementation. As a case study, we implement the framework in the context of Indian food platters known for their complex presentation that poses a challenge for the automated detection of dishes. Starting with the 61 most popular Indian dishes, we identify the state-of-the-art model through a comparative analysis of deep-learning-based object detection architectures. Rooted in a meticulous compilation of 68,005 platter images with 134,814 manual dish annotations, we first compare ten architectures for multi-label classification to identify ResNet152 (mAP=84.51%) as the best model. YOLOv8x (mAP=87.70%) emerged as the best model architecture for dish detection among the eight deep-learning models implemented after a thorough performance evaluation. By comparing with the state-of-the-art model for the IndianFood10 dataset, we demonstrate the superior object detection performance of YOLOv8x for this subset and establish Resnet152 as the best architecture for multi-label classification. The models thus trained on richly annotated data can be extended to include dishes from across global cuisines. The proposed framework is demonstrated through a proof-of-concept mobile application with diverse applications for diet logging, food recommendation systems, nutritional interventions, and mitigation of lifestyle disorders.

arXiv:2305.07528공식 코드 · Papers with Code

WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models

The open road poses many challenges to autonomous perception, including poor visibility from extreme weather conditions. Models trained on good-weather datasets frequently fail at detection in these out-of-distribution settings. To aid adversarial robustness in perception, we introduce WEDGE (WEather images by DALL-E GEneration): a synthetic dataset generated with a vision-language generative model via prompting. WEDGE consists of 3360 images in 16 extreme weather conditions manually annotated with 16513 bounding boxes, supporting research in the tasks of weather classification and 2D object detection. We have analyzed WEDGE from research standpoints, verifying its effectiveness for extreme-weather autonomous perception. We establish baseline performance for classification and detection with 53.87% test accuracy and 45.41 mAP. Most importantly, WEDGE can be used to fine-tune state-of-the-art detectors, improving SOTA performance on real-world weather benchmarks (such as DAWN) by 4.48 AP for well-generated classes like trucks. WEDGE has been collected under OpenAI's terms of use and is released for public use under the CC BY-NC-SA 4.0 license. The repository for this work and dataset is available at https://infernolia.github.io/WEDGE.

arXiv:2305.07522

SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving

3D object detection using point cloud (PC) data is essential for perception pipelines of autonomous driving, where efficient encoding is key to meeting stringent resource and latency requirements. PointPillars, a widely adopted bird's-eye view (BEV) encoding, aggregates 3D point cloud data into 2D pillars for fast and accurate 3D object detection. However, the state-of-the-art methods employing PointPillars overlook the inherent sparsity of pillar encoding where only a valid pillar is encoded with a vector of channel elements, missing opportunities for significant computational reduction. Meanwhile, current sparse convolution accelerators are designed to handle only element-wise activation sparsity and do not effectively address the vector sparsity imposed by pillar encoding. In this paper, we propose SPADE, an algorithm-hardware co-design strategy to maximize vector sparsity in pillar-based 3D object detection and accelerate vector-sparse convolution commensurate with the improved sparsity. SPADE consists of three components: (1) a dynamic vector pruning algorithm balancing accuracy and computation savings from vector sparsity, (2) a sparse coordinate management hardware transforming 2D systolic array into a vector-sparse convolution accelerator, and (3) sparsity-aware dataflow optimization tailoring sparse convolution schedules for hardware efficiency. Taped-out with a commercial technology, SPADE saves the amount of computation by 36.3--89.2\% for representative 3D object detection networks and benchmarks, leading to 1.3--10.9$\times$ speedup and 1.5--12.6$\times$ energy savings compared to the ideal dense accelerator design. These sparsity-proportional performance gains equate to 4.1--28.8$\times$ speedup and 90.2--372.3$\times$ energy savings compared to the counterpart server and edge platforms.

arXiv:2305.07304공식 코드 · Papers with Code

CLIP-Count: Towards Text-Guided Zero-Shot Object Counting

Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object counting, however, remains a formidable challenge. In this study, we first investigate transferring vision-language models (VLMs) for class-agnostic object counting. Specifically, we propose CLIP-Count, the first end-to-end pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner. To align the text embedding with dense visual features, we introduce a patch-text contrastive loss that guides the model to learn informative patch-level visual representations for dense prediction. Moreover, we design a hierarchical patch-text interaction module to propagate semantic information across different resolution levels of visual features. Benefiting from the full exploitation of the rich image-text alignment knowledge of pretrained VLMs, our method effectively generates high-quality density maps for objects-of-interest. Extensive experiments on FSC-147, CARPK, and ShanghaiTech crowd counting datasets demonstrate state-of-the-art accuracy and generalizability of the proposed method. Code is available: https://github.com/songrise/CLIP-Count.

arXiv:2305.06940공식 코드 · Papers with Code

SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving

Object detection (OD) is crucial to autonomous driving. On the other hand, unknown objects, which have not been seen in training sample set, are one of the reasons that hinder autonomous vehicles from driving beyond the operational domain. To addresss this issue, we propose a saliency-based OD algorithm (SalienDet) to detect unknown objects. Our SalienDet utilizes a saliency-based algorithm to enhance image features for object proposal generation. Moreover, we design a dataset relabeling approach to differentiate the unknown objects from all objects in training sample set to achieve Open-World Detection. To validate the performance of SalienDet, we evaluate SalienDet on KITTI, nuScenes, and BDD datasets, and the result indicates that it outperforms existing algorithms for unknown object detection. Notably, SalienDet can be easily adapted for incremental learning in open-world detection tasks. The project page is \url{https://github.com/dingmike001/SalienDet-Open-Detection.git}.

arXiv:2305.06820

DeepSTEP -- Deep Learning-Based Spatio-Temporal End-To-End Perception for Autonomous Vehicles

Autonomous vehicles demand high accuracy and robustness of perception algorithms. To develop efficient and scalable perception algorithms, the maximum information should be extracted from the available sensor data. In this work, we present our concept for an end-to-end perception architecture, named DeepSTEP. The deep learning-based architecture processes raw sensor data from the camera, LiDAR, and RaDAR, and combines the extracted data in a deep fusion network. The output of this deep fusion network is a shared feature space, which is used by perception head networks to fulfill several perception tasks, such as object detection or local mapping. DeepSTEP incorporates multiple ideas to advance state of the art: First, combining detection and localization into a single pipeline allows for efficient processing to reduce computational overhead and further improves overall performance. Second, the architecture leverages the temporal domain by using a self-attention mechanism that focuses on the most important features. We believe that our concept of DeepSTEP will advance the development of end-to-end perception systems. The network will be deployed on our research vehicle, which will be used as a platform for data collection, real-world testing, and validation. In conclusion, DeepSTEP represents a significant advancement in the field of perception for autonomous vehicles. The architecture's end-to-end design, time-aware attention mechanism, and integration of multiple perception tasks make it a promising solution for real-world deployment. This research is a work in progress and presents the first concept of establishing a novel perception pipeline.

arXiv:2305.06773

Towards a Better Understanding of the Computer Vision Research Community in Africa

Computer vision is a broad field of study that encompasses different tasks (e.g., object detection). Although computer vision is relevant to the African communities in various applications, yet computer vision research is under-explored in the continent and constructs only 0.06% of top-tier publications in the last ten years. In this paper, our goal is to have a better understanding of the computer vision research conducted in Africa and provide pointers on whether there is equity in research or not. We do this through an empirical analysis of the African computer vision publications that are Scopus indexed, where we collect around 63,000 publications over the period 2012-2022. We first study the opportunities available for African institutions to publish in top-tier computer vision venues. We show that African publishing trends in top-tier venues over the years do not exhibit consistent growth, unlike other continents such as North America or Asia. Moreover, we study all computer vision publications beyond top-tier venues in different African regions to find that mainly Northern and Southern Africa are publishing in computer vision with 68.5% and 15.9% of publications, resp. Nonetheless, we highlight that both Eastern and Western Africa are exhibiting a promising increase with the last two years closing the gap with Southern Africa. Additionally, we study the collaboration patterns in these publications to find that most of these exhibit international collaborations rather than African ones. We also show that most of these publications include an African author that is a key contributor as the first or last author. Finally, we present the most recurring keywords in computer vision publications per African region.

arXiv:2305.07011공식 코드 · Papers with Code

Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers

We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we propose to randomly crop and resize regions of positional embeddings instead of using the whole image positional embeddings. This better matches the use of positional embeddings at region-level in the detection finetuning phase. In addition, we replace the common softmax cross entropy loss in contrastive learning with focal loss to better learn the informative yet difficult examples. Finally, we leverage recent advances in novel object proposals to improve open-vocabulary detection finetuning. We evaluate our full model on the LVIS and COCO open-vocabulary detection benchmarks and zero-shot transfer. RO-ViT achieves a state-of-the-art 34.1 $AP_r$ on LVIS, surpassing the best existing approach by +7.8 points in addition to competitive zero-shot transfer detection. Surprisingly, RO-ViT improves the image-level representation as well and achieves the state of the art on 9 out of 12 metrics on COCO and Flickr image-text retrieval benchmarks, outperforming competitive approaches with larger models.

arXiv:2305.05836

Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection

Accurate Named Entity Recognition (NER) is crucial for various information retrieval tasks in industry. However, despite significant progress in traditional NER methods, the extraction of Complex Named Entities remains a relatively unexplored area. In this paper, we propose a novel system that combines object detection for Document Layout Analysis (DLA) with weakly supervised learning to address the challenge of extracting discontinuous complex named entities in legal documents. Notably, to the best of our knowledge, this is the first work to apply weak supervision to DLA. Our experimental results show that the model trained solely on pseudo labels outperforms the supervised baseline when gold-standard data is limited, highlighting the effectiveness of our proposed approach in reducing the dependency on annotated data.

arXiv:2305.05726

Vision-Language Models in Remote Sensing: Current Progress and Future Trends

The remarkable achievements of ChatGPT and GPT-4 have sparked a wave of interest and research in the field of large language models for Artificial General Intelligence (AGI). These models provide intelligent solutions close to human thinking, enabling us to use general artificial intelligence to solve problems in various applications. However, in remote sensing (RS), the scientific literature on the implementation of AGI remains relatively scant. Existing AI-related research in remote sensing primarily focuses on visual understanding tasks while neglecting the semantic understanding of the objects and their relationships. This is where vision-language models excel, as they enable reasoning about images and their associated textual descriptions, allowing for a deeper understanding of the underlying semantics. Vision-language models can go beyond visual recognition of RS images, model semantic relationships, and generate natural language descriptions of the image. This makes them better suited for tasks requiring visual and textual understanding, such as image captioning, and visual question answering. This paper provides a comprehensive review of the research on vision-language models in remote sensing, summarizing the latest progress, highlighting challenges, and identifying potential research opportunities.

arXiv:2305.05423

High-throughput Cotton Phenotyping Big Data Pipeline Lambda Architecture Computer Vision Deep Neural Networks

In this study, we propose a big data pipeline for cotton bloom detection using a Lambda architecture, which enables real-time and batch processing of data. Our proposed approach leverages Azure resources such as Data Factory, Event Grids, Rest APIs, and Databricks. This work is the first to develop and demonstrate the implementation of such a pipeline for plant phenotyping through Azure's cloud computing service. The proposed pipeline consists of data preprocessing, object detection using a YOLOv5 neural network model trained through Azure AutoML, and visualization of object detection bounding boxes on output images. The trained model achieves a mean Average Precision (mAP) score of 0.96, demonstrating its high performance for cotton bloom classification. We evaluate our Lambda architecture pipeline using 9000 images yielding an optimized runtime of 34 minutes. The results illustrate the scalability of the proposed pipeline as a solution for deep learning object detection, with the potential for further expansion through additional Azure processing cores. This work advances the scientific research field by providing a new method for cotton bloom detection on a large dataset and demonstrates the potential of utilizing cloud computing resources, specifically Azure, for efficient and accurate big data processing in precision agriculture.

arXiv:2305.05260

Guided Focal Stack Refinement Network for Light Field Salient Object Detection

Light field salient object detection (SOD) is an emerging research direction attributed to the richness of light field data. However, most existing methods lack effective handling of focal stacks, therefore making the latter involved in a lot of interfering information and degrade the performance of SOD. To address this limitation, we propose to utilize multi-modal features to refine focal stacks in a guided manner, resulting in a novel guided focal stack refinement network called GFRNet. To this end, we propose a guided refinement and fusion module (GRFM) to refine focal stacks and aggregate multi-modal features. In GRFM, all-in-focus (AiF) and depth modalities are utilized to refine focal stacks separately, leading to two novel sub-modules for different modalities, namely AiF-based refinement module (ARM) and depth-based refinement module (DRM). Such refinement modules enhance structural and positional information of salient objects in focal stacks, and are able to improve SOD accuracy. Experimental results on four benchmark datasets demonstrate the superiority of our GFRNet model against 12 state-of-the-art models.

arXiv:2305.05511공식 코드 · Papers with Code

Self-supervised dense representation learning for live-cell microscopy with time arrow prediction

State-of-the-art object detection and segmentation methods for microscopy images rely on supervised machine learning, which requires laborious manual annotation of training data. Here we present a self-supervised method based on time arrow prediction pre-training that learns dense image representations from raw, unlabeled live-cell microscopy videos. Our method builds upon the task of predicting the correct order of time-flipped image regions via a single-image feature extractor followed by a time arrow prediction head that operates on the fused features. We show that the resulting dense representations capture inherently time-asymmetric biological processes such as cell divisions on a pixel-level. We furthermore demonstrate the utility of these representations on several live-cell microscopy datasets for detection and segmentation of dividing cells, as well as for cell state classification. Our method outperforms supervised methods, particularly when only limited ground truth annotations are available as is commonly the case in practice. We provide code at https://github.com/weigertlab/tarrow.

arXiv:2305.05499

Effects of Real-Life Traffic Sign Alteration on YOLOv7- an Object Recognition Model

The widespread adoption of Image Processing has propelled Object Recognition (OR) models into essential roles across various applications, demonstrating the power of AI and enabling crucial services. Among the applications, traffic sign recognition stands out as a popular research topic, given its critical significance in the development of autonomous vehicles. Despite their significance, real-world challenges, such as alterations to traffic signs, can negatively impact the performance of OR models. This study investigates the influence of altered traffic signs on the accuracy and effectiveness of object recognition, employing a publicly available dataset to introduce alterations in shape, color, content, visibility, angles and background. Focusing on the YOLOv7 (You Only Look Once) model, the study demonstrates a notable decline in detection and classification accuracy when confronted with traffic signs in unusual conditions including the altered traffic signs. Notably, the alterations explored in this study are benign examples and do not involve algorithms used for generating adversarial machine learning samples. This study highlights the significance of enhancing the robustness of object detection models in real-life scenarios and the need for further investigation in this area to improve their accuracy and reliability.

arXiv:2305.04833

Revisiting Table Detection Datasets for Visually Rich Documents

Table Detection has become a fundamental task for visually rich document understanding with the surging number of electronic documents. However, popular public datasets widely used in related studies have inherent limitations, including noisy and inconsistent samples, limited training samples, and limited data sources. These limitations make these datasets unreliable to evaluate the model performance and cannot reflect the actual capacity of models. Therefore, this study revisits some open datasets with high-quality annotations, identifies and cleans the noise, and aligns the annotation definitions of these datasets to merge a larger dataset, termed Open-Tables. Moreover, to enrich the data sources, we propose a new ICT-TD dataset using the PDF files of Information and Communication Technologies (ICT) commodities, a different domain containing unique samples that hardly appear in open datasets. To ensure the label quality of the dataset, we annotated the dataset manually following the guidance of a domain expert. The proposed dataset is challenging and can be a sample of actual cases in the business context. We built strong baselines using various state-of-the-art object detection models. Our experimental results show that the domain differences among existing open datasets are minor despite having different data sources. Our proposed Open-Tables and ICT-TD can provide a more reliable evaluation for models because of their high quality and consistent annotations. Besides, they are more suitable for cross-domain settings. Our experimental results show that in the cross-domain setting, benchmark models trained with cleaned Open-Tables dataset can achieve 0.6\%-2.6\% higher weighted average F1 than the corresponding ones trained with the noisy version of Open-Tables, demonstrating the reliability of the proposed datasets. The datasets are public available.

arXiv:2305.04396

SegGPT Meets Co-Saliency Scene

Co-salient object detection targets at detecting co-existed salient objects among a group of images. Recently, a generalist model for segmenting everything in context, called SegGPT, is gaining public attention. In view of its breakthrough for segmentation, we can hardly wait to probe into its contribution to the task of co-salient object detection. In this report, we first design a framework to enable SegGPT for the problem of co-salient object detection. Proceed to the next step, we evaluate the performance of SegGPT on the problem of co-salient object detection on three available datasets. We achieve a finding that co-saliency scenes challenges SegGPT due to context discrepancy within a group of co-saliency images.

arXiv:2305.04170

YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification

In this study, we examine the associations between channel features and convolutional kernels during the processes of feature purification and gradient backpropagation, with a focus on the forward and backward propagation within the network. Consequently, we propose a method called Dense Channel Compression for Feature Spatial Solidification. Drawing upon the central concept of this method, we introduce two innovative modules for backbone and head networks: the Dense Channel Compression for Feature Spatial Solidification Structure (DCFS) and the Asymmetric Multi-Level Compression Decoupled Head (ADH). When integrated into the YOLOv5 model, these two modules demonstrate exceptional performance, resulting in a modified model referred to as YOLOCS. Evaluated on the MSCOCO dataset, the large, medium, and small YOLOCS models yield AP of 50.1%, 47.6%, and 42.5%, respectively. Maintaining inference speeds remarkably similar to those of the YOLOv5 model, the large, medium, and small YOLOCS models surpass the YOLOv5 model's AP by 1.1%, 2.3%, and 5.2%, respectively.