In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge. This project is designed to challenge the computer vision community to develop robust image captioning models that advance the state-of-the-art both in terms of accuracy and fairness. Through the challenge, the image captioning models were tested using a new evaluation dataset that includes a large variety of visual concepts from many domains. There was no specific training data provided for the challenge, and therefore the challenge entries were required to adapt to new types of image descriptions that had not been seen during training. This report includes information on the newly proposed NICE dataset, evaluation methods, challenge results, and technical details of top-ranking entries. We expect that the outcomes of the challenge will contribute to the improvement of AI models on various vision-language tasks.

pdf/nice-cvpr-2023-challenge-on-zero-shot-image-captioning-3233e8p003.pdf

NICE: CVPR 2023 Challenge on Zero-shot Image Captioning

Accurate road network data for open-pit mine is crucial for the effective implementation of ore mining and transportation scheduling systems as well as the operation of unmanned mining trucks. It is still a challenging task to accurately extract roads from open-pit mine because of their blurred boundaries and varying scales. Based on the characteristics of open-pit mine roads, we propose a local point feature enhancement network (LPFE-Net). The core of LPFE-Net is a point feature enhancement unit (PFE Unit) and a multiscale residual module. Among them, the PFE unit is used to fuse the key features of the neighboring points. The multiscale residual module superimposes the PFE unit to expand the perceptual field and uses multilevel residual connections to improve information flow and reduce model complexity. The experimental results show that the proposed LPFE-Net outperforms all the compared methods in the open-pit mine road extraction task while having a relatively fast extraction speed.

Road Extraction From Point Clouds of Open-Pit Mine Using LPFE-Net

Over recent decades, significant advancements in cross-modal retrieval is mainly driven by breakthroughs in visual and linguistic modeling. However, a recent study shows that multi-modal data representations tend to cluster within a limited convex cone (as representation degeneration problem), which hinders retrieval performance due to the inseparability of these representations. In our study, we first empirically validate the presence of the representation degeneration problem across multiple cross-modal benchmarks and methods. Next, to address it, we introduce a novel method, called InvGC, a post-processing technique inspired by graph convolution and average pooling. Specifically, InvGC defines the graph topology within the datasets and then applies graph convolution in a subtractive manner. This method effectively separates representations by increasing the distances between data points. To improve the efficiency and effectiveness of InvGC, we propose an advanced graph topology, LocalAdj, which only aims to increase the distances between each data point and its nearest neighbors. To understand why InvGC works, we present a detailed theoretical analysis, proving that the lower bound of recall will be improved after deploying InvGC. Extensive empirical results show that InvGC and InvGC w/LocalAdj significantly mitigate the representation degeneration problem, thereby enhancing retrieval performance. 

pdf/invgc-robust-cross-modal-retrieval-by-inverse-graph-3ksa8uvut6.pdf

InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution

Radiology report generation (RRG) is crucial to save the valuable time of radiologists in drafting the report, therefore increasing their work efficiency. Compared to typical methods that directly transfer image captioning technologies to RRG, our approach incorporates organ-wise priors into the report generation. Specifically, in this paper, we propose Organ-aware Diagnosis (OaD) to generate diagnostic reports containing descriptions of each physiological organ. During training, we first develop a task distillation (TD) module to extract organ-level descriptions from reports. We then introduce an organ-aware report generation module that, for one thing, provides a specific description for each organ, and for another, simulates clinical situations to provide short descriptions for normal cases. Furthermore, we design an auto-balance mask loss to ensure balanced training for normal/abnormal descriptions and various organs simultaneously. Being intuitively reasonable and practically simple, our OaD outperforms SOTA alternatives by large margins on commonly used IU-Xray and MIMIC-CXR datasets, as evidenced by a 3.4% BLEU-1 improvement on MIMIC-CXR and 2.0% BLEU-2 improvement on IU-Xray. 

An Organ-aware Diagnosis Framework for Radiology Report Generation

Rayleigh waves are highly sensitive to surface and subsurface defects. However, the varying surface profiles of complex structures induce constant changes in the Rayleigh waveform. Furthermore, Rayleigh waves encompass multi-dimensional characteristics of subsurface defects, significantly increasing the difficulty of quantitatively detecting the sizes of subsurface defects in different dimensions. This paper presents a machine learning (ML)-based method for quantitatively detecting subsurface defect depth and width in curved structures using laser-generated Rayleigh waves. An experimentally validated finite element model is first established to construct a dataset of Rayleigh wave signals labeled with multidimensional subsurface defect sizes. The dataset is augmented from 188 to 368 samples using the Mix-up algorithm, with additional experimental signals incorporated. Feature parameters of Rayleigh waves are extracted in both time and frequency domains through waveform analysis and sliding window wavelet transform (SWT). These features are used to train ML models: Gaussian Process (GP), Extreme Gradient Boosting (XGBoost), and Random Forest (RF). Comparative results demonstrate GP achieves the highest prediction accuracy for subsurface defect depth and width on the test set, reaching 98.64% and 97.73%, respectively. The study highlights the integration of experimental and simulated data in training, which reduces costs while enhancing model robustness in practical applications. 

Quantitative detection of the width and depth of subsurface defects in curved structures using ultrasonic Rayleigh waves

Understanding point cloud has recently gained huge interests following the development of 3D scanning devices and the accumulation of large-scale 3D data. Most point cloud processing algorithms can be classified as either point-based or voxel-based methods, both of which have severe limitations in processing time or memory, or both. To overcome these limitations, we propose Projection-based Point Convolution (PPConv), a point convolutional module that uses 2D convolutions and multi-layer perceptrons (MLPs) as its components. In PPConv, point features are processed through two branches: point branch and projection branch. Point branch consists of MLPs, while projection branch transforms point features into a 2D feature map and then apply 2D convolutions. As PPConv does not use point-based or voxel-based convolutions, it has advantages in fast point cloud processing. When combined with a learnable projection and effective feature fusion strategy, PPConv achieves superior efficiency compared to state-of-the-art methods, even with a simple architecture based on PointNet++. We demonstrate the efficiency of PPConv in terms of the trade-off between inference time and segmentation performance. The experimental results on S3DIS and ShapeNetPart show that PPConv is the most efficient method among the compared ones. The code is available at github.com/pahn04/PPConv.

pdf/projection-based-point-convolution-for-efficient-point-cloud-26khav3t.pdf

Projection-Based Point Convolution for Efficient Point Cloud Segmentation

When trained on large-scale datasets, image captioning models can understand the content of images from a general domain but often fail to generate accurate, detailed captions. To improve performance, pretraining-and-finetuning has been a key strategy for image captioning. However, we find that large-scale bidirectional training between image and text enables zero-shot image captioning. In this paper, we introduce Bidirectional Image Text Training in largER Scale, BITTERS, an efficient training and inference framework for zero-shot image captioning. We also propose a new evaluation benchmark which comprises of high quality datasets and an extensive set of metrics to properly evaluate zero-shot captioning accuracy and societal bias. We additionally provide an efficient finetuning approach for keyword extraction. We show that careful selection of large-scale training set and model architecture is the key to achieving zero-shot image captioning.

https://export.arxiv.org/pdf/2211.06774v3.pdf

Large-Scale Bidirectional Training for Zero-Shot Image Captioning

While deep neural networks have achieved remarkable performance, data augmentation has emerged as a crucial strategy to mitigate overfitting and enhance network performance. These techniques hold particular significance in industrial manufacturing contexts. Recently, image mixing-based methods have been introduced, exhibiting improved performance on public benchmark datasets. However, their application to industrial tasks remains challenging. The manufacturing environment generates massive amounts of unlabeled data on a daily basis, with only a few instances of abnormal data occurrences. This leads to severe data imbalance. Thus, creating well-balanced datasets is not straightforward due to the high costs associated with labeling. Nonetheless, this is a crucial step for enhancing productivity. For this reason, we introduce ContextMix, a method tailored for industrial applications and benchmark datasets. ContextMix generates novel data by resizing entire images and integrating them into other images within the batch. This approach enables our method to learn discriminative features based on varying sizes from resized images and train informative secondary features for object recognition using occluded images. With the minimal additional computation cost of image resizing, ContextMix enhances performance compared to existing augmentation techniques. We evaluate its effectiveness across classification, detection, and segmentation tasks using various network architectures on public benchmark datasets. Our proposed method demonstrates improved results across a range of robustness tasks. Its efficacy in real industrial environments is particularly noteworthy, as demonstrated using the passive component dataset. 

ContextMix: A context-aware data augmentation method for industrial visual inspection systems

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Pyunghwan Ahn

Author Tools

Chat about Author

Papers

Projection-Based Point Convolution for Efficient Point Cloud Segmentation

NICE: CVPR 2023 Challenge on Zero-shot Image Captioning

Large-Scale Bidirectional Training for Zero-Shot Image Captioning

ContextMix: A context-aware data augmentation method for industrial visual inspection systems