Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation
School of Software Engineering, Sun Yat-sen University（中山大学软件学院）；Nanjing University（南京大学）；College of Management and Economics, Tianjin University（天津大学管理学院）
While Diffusion Models excel in text-to-image synthesis, they frequently suffer from catastrophic concept omission when generating complex multi-instance scenes. Existing training-free methods attempt to resolve this by rescaling attention maps, which merely exacerbates unstructured noise without establishing coherent semantic representations. To address this, we propose Delta-K, a backbone-agnostic, plug-and-play inference framework that resolves omission by operating directly in the shared cross-attention Key space. Utilizing a lightweight Vision-Language Model (VLM) preview, we isolate a differential key ($ΔK$) capturing the pure semantic signature of missing concepts, and proactively inject it during the early semantic planning phase. Governed by a dynamically optimized scheduling mechanism, Delta-K grounds diffuse noise into stable structural anchors while naturally preserving existing concepts via the inherent orthogonality of $ΔK$. Extensive experiments validate its universal applicability, demonstrating that Delta-K significantly improves compositional alignment across both modern DiT and foundational U-Net architectures without requiring spatial masks, auxiliary training, or structural modifications.
Boosting Knowledge Graph-based Recommendations through Confidence-Aware Augmentation with Large Language Models
University of Science and Technology of China（中国科学技术大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement
AiLECS Lab Monash University Melbourne, Australia（AiLECS实验室 墨尔本大学 澳大利亚）；School of Social Sciences Monash University Melbourne, Australia（社会科学学院 墨尔本大学 澳大利亚）
Boosting Dermatoscopic Lesion Segmentation via Diffusion Models with Visual and Textual Prompts
Shanghai Artificial Intelligence Lab（上海人工智能实验室）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of California Santa Cruz（加利福尼亚大学圣克鲁兹分校）；West China Biomedical Big Data Center, Sichuan University West China Hospital（四川大学华西医院华西生物医学大数据中心）
As more and more artificial intelligence (AI) technologies move from the laboratory to real-world applications, the open-set and robustness challenges brought by data from the real world have received increasing attention. Data augmentation is a widely used method to improve model performance, and some recent works have also confirmed its positive effect on the robustness of AI models. However, most of the existing data augmentation methods are heuristic, lacking the exploration of their internal mechanisms. We apply the explainable artificial intelligence (XAI) method, explore the internal me…
Deep Neural Networks (DNNs) show a significant impact on medical imaging. One significant problem with adopting DNNs for skin cancer classification is that the class frequencies in the existing datasets are imbalanced. This problem hinders the training of robust and well-generalizing models. Data Augmentation addresses this by using existing data more effectively. However, standard data augmentation implementations are manually designed and produce only limited reasonably alternative data. Instead, Generative Adversarial Networks (GANs) is utilized to generate a much broader set of augmentatio…
Mississippi State University（密西西比州立大学）；Michigan State University（密歇根州立大学）；United States Department of Agriculture, Agricultural Research Service（美国农业部农业研究局）
In agricultural image analysis, optimal model performance is keenly pursued for better fulfilling visual recognition tasks (e.g., image classification, segmentation, object detection and localization), in the presence of challenges with biological variability and unstructured environments. Large-scale, balanced and ground-truthed image datasets, however, are often difficult to obtain to fuel the development of advanced, high-performance models. As artificial intelligence through deep learning is impacting analysis and modeling of agricultural images, data augmentation plays a crucial role in b…
Bosch Center for Artificial Intelligence（博世人工智能中心）
Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we introduce a novel augmentation scheme designed specifically for GAN-based semantic image synthesis models. We propose to randomly warp object shapes in the semantic label maps used as an input to the generator. The local shape discrepancies between the warped and non-warped label maps and images enable the GAN to learn better the structural and geometric details…
Data61-CSIRO（Data61-联邦科学与工业研究组织）；Australian National University（澳大利亚国立大学）；University of Adelaide（阿德莱德大学）
We present You Only Cut Once (YOCO) for performing data augmentations. YOCO cuts one image into two pieces and performs data augmentations individually within each piece. Applying YOCO improves the diversity of the augmentation per sample and encourages neural networks to recognize objects from partial information. YOCO enjoys the properties of parameter-free, easy usage, and boosting almost all augmentations for free. Thorough experiments are conducted to evaluate its effectiveness. We first demonstrate that YOCO can be seamlessly applied to varying data augmentations, neural network architec…
While efficient architectures and a plethora of augmentations for end-to-end image classification tasks have been suggested and heavily investigated, state-of-the-art techniques for audio classifications still rely on numerous representations of the audio signal together with large architectures, fine-tuned from large datasets. By utilizing the inherited lightweight nature of audio and novel audio augmentations, we were able to present an efficient end-to-end network with strong generalization ability. Experiments on a variety of sound classification sets demonstrate the effectiveness and robu…
South China University of Technology（华南理工大学）；University of Utah（犹他大学）
We introduce the idea of inter-slice image augmentation whereby the numbers of the medical images and the corresponding segmentation labels are increased between two consecutive images in order to boost medical image segmentation accuracy. Unlike conventional data augmentation methods in medical imaging, which only increase the number of training samples directly by adding new virtual samples using simple parameterized transformations such as rotation, flipping, scaling, etc., we aim to augment data based on the relationship between two consecutive images, which increases not only the number b…
Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training
School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Chongqing Academy of Science and Technology（重庆科学技术研究院）；Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系）
The University of Adelaide（阿德莱德大学）；Adobe Inc.（Adobe公司）；Zhejiang University（浙江大学）
Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Composition-1k/alphamatting.com). However, the robustness, including robustness to trimaps and generalization to images from different domains, is still under-explored. Although some works propose to either refine the trimaps or adapt the algorithms to real-world images via extra data augmentation, none of them has taken both into consideration, not to mention the significant performance deterioration on benchmarks while using those data augmentation. To fill this gap, we propose an image matting method w…
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）；University of Cambridge（剑桥大学）；Cancer Research UK Cambridge Institute（英国癌症研究院剑桥研究所）；University of Milano-Bicocca（米兰比可卡大学）；Chubu University（中部大学）；Jikei University School of Medicine（东京慈惠会医科大学）；Kyushu University（九州大学）
Convolutional Neural Networks (CNNs) achieve excellent computer-assisted diagnosis with sufficient annotated training data. However, most medical imaging datasets are small and fragmented. In this context, Generative Adversarial Networks (GANs) can synthesize realistic/diverse additional training images to fill the data lack in the real image distribution; researchers have improved classification by augmenting data with noise-to-image (e.g., random noise samples to diverse pathological images) or image-to-image GANs (e.g., a benign image to a malignant one). Yet, no research has reported resul…
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；Department of Engineering Science, University of Oxford（牛津大学工程科学系）；School of Engineering, Newcastle University（纽卡斯尔大学工程学院）
The recent advance in deep generative models outlines a promising perspective in the realm of Zero-Shot Learning (ZSL). Most generative ZSL methods use category semantic attributes plus a Gaussian noise to generate visual features. After generating unseen samples, this family of approaches effectively transforms the ZSL problem into a supervised classification scheme. However, the existing models use a single semantic attribute, which contains the complete attribute information of the category. The generated data also carry the complete attribute information, but in reality, visual samples usu…
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Continuous sign language recognition (SLR) deals with unaligned video-text pair and uses the word error rate (WER), i.e., edit distance, as the main evaluation metric. Since it is not differentiable, we usually instead optimize the learning model with the connectionist temporal classification (CTC) objective loss, which maximizes the posterior probability over the sequential alignment. Due to the optimization gap, the predicted sentence with the highest decoding probability may not be the best choice under the WER metric. To tackle this issue, we propose a novel architecture with cross modalit…
Edith Cowan University（伊迪斯科文大学）；University of Western Australia（西澳大学）
COVID-19 classification using chest Computed Tomography (CT) has been found pragmatically useful by several studies. Due to the lack of annotated samples, these studies recommend transfer learning and explore the choices of pre-trained models and data augmentation. However, it is still unknown if there are better strategies than vanilla transfer learning for more accurate COVID-19 classification with limited CT data. This paper provides an affirmative answer, devising a novel `model' augmentation technique that allows a considerable performance boost to transfer learning for the task. Our meth…
University of New South Wales（新南威尔士大学）；School of Minerals and Energy Resources Engineering（矿物与能源资源工程学院）
Digital Rock Imaging is constrained by detector hardware, and a trade-off between the image field of view (FOV) and the image resolution must be made. This can be compensated for with super resolution (SR) techniques that take a wide FOV, low resolution (LR) image, and super resolve a high resolution (HR), high FOV image. The Enhanced Deep Super Resolution Generative Adversarial Network (EDSRGAN) is trained on the Deep Learning Digital Rock Super Resolution Dataset, a diverse compilation 12000 of raw and processed uCT images. The network shows comparable performance of 50% to 70% reduction in …
Boosting Classification with Quantum-Inspired Augmentations
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；RPTU Kaiserslautern-Landau（科隆-兰道大学）；Department of Computer Science and Research Initiative QC-AI（计算机科学系和量子人工智能研究计划）；Department of Physics（物理系）
Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average
Daegu-Gyeongbuk Research Center, Electronics and Telecommunications Research Institute (ETRI)（大邱-庆尚研究中心，电子电信研究所）
Improving multi-view aggregation is integral for multi-view pedestrian detection, which aims to obtain a bird's-eye-view pedestrian occupancy map from images captured through a set of calibrated cameras. Inspired by the success of attention modules for deep neural networks, we first propose a Homography Attention Module (HAM) which is shown to boost the performance of existing end-to-end multiview detection approaches by utilizing a novel channel gate and spatial gate. Additionally, we propose Booster-SHOT, an end-to-end convolutional approach to multiview pedestrian detection incorporating ou…
Boosting Overlapping Organoid Instance Segmentation Using Pseudo-Label Unmixing and Synthesis-Assisted Learning
School of Biomedical Engineering, Sun Yat-sen University（中山大学生物医学工程学院）；Peng Cheng Laboratory（鹏城实验室）；The First Affiliated Hospital of Shenzhen University, Shenzhen Second People's Hospital（深圳大学第一附属医院、深圳第二人民医院）；The Research Center of Clinical Medicine, Affiliated Hospital of Nantong University, Medical School of Nantong University（临床医学研究中心、南通大学附属医院、南通大学医学院）；Cixi Institute of Biomedical Engineering, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences（慈溪生物医学工程研究所、宁波材料技术与工程研究所、中国科学院）
RareSpot: Spotting Small and Rare Wildlife in Aerial Imagery with Multi-Scale Consistency and Context-Aware Augmentation
University of California, Santa Barbara（加州大学圣芭芭拉分校）；Smithsonian National Zoo and Conservation Biology Institute（史密森尼国家动物园与保护生物学研究所）；Stanford University（斯坦福大学）
In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net. The embedded ``Selective Position Encoding (SPE)'' procedure relies on an attention mechanism that can effectively attend to the underlying rotation condition of the input. Such encoded rotation condition then determines which part of the network parameters to be focused on, and is shown to efficiently help reduce the degree of freedom of the optimization during training. This mechanism henceforth can better leverage the rotation augmentations through reduced training difficulties, m…
Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and increase the diversity, previous methods have investigated using data annotation from other domain (e.g. bbox, point) in a weakly supervised mechanism. In this paper, we present a simple, efficient and effective method to augment the training set using the existing instance mask annotations. Exploiting the pixel redundancy of the background, we are able to improve the performance of Mask R-CNN for 1.7 mAP on COCO datas…
Although transformer networks are recently employed in various vision tasks with outperforming performance, extensive training data and a lengthy training time are required to train a model to disregard an inductive bias. Using trainable links between the channel-wise spatial attention of a pre-trained Convolutional Neural Network (CNN) and the attention head of Vision Transformers (ViT), we present a regularization technique to improve the training efficiency of ViT. The trainable links are referred to as the attention augmentation module, which is trained simultaneously with ViT, boosting th…
PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts
State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Information Science and Technology, ShanghaiTech University（上海科技大学信息科学与技术学院）；OPPO（OPPO公司）
Boosting Illuminant Estimation in Deep Color Constancy through Enhancing Brightness Robustness
School of Computer Science and Cyber Engineering, Guangzhou University（广州大学计算机科学与网络工程学院）；State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）；Information Security Research Group, University College London（伦敦大学学院信息安全研究组）
The Hong Kong Polytechnic University（香港理工大学）；South China University of Technology（华南理工大学）
It is well-known that the performance of well-trained deep neural networks may degrade significantly when they are applied to data with even slightly shifted distributions. Recent studies have shown that introducing certain perturbation on feature statistics (\eg, mean and standard deviation) during training can enhance the cross-domain generalization ability. Existing methods typically conduct such perturbation by utilizing the feature statistics within a mini-batch, limiting their representation capability. Inspired by the domain generalization objective, we introduce a novel Adversarial Sty…
Vicomtech Foundation, Basque Research and Technology Alliance (BRTA)（维康科技基金会，巴斯克研究与技术联盟（BRTA））；University of the Basque Country（巴斯克大学）
In this paper, we address the problem of face recognition with masks. Given the global health crisis caused by COVID-19, mouth and nose-covering masks have become an essential everyday-clothing-accessory. This sanitary measure has put the state-of-the-art face recognition models on the ropes since they have not been designed to work with masked faces. In addition, the need has arisen for applications capable of detecting whether the subjects are wearing masks to control the spread of the virus. To overcome these problems a full training pipeline is presented based on the ArcFace work, with sev…
Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models
Southern University of Science and Technology（南方科技大学）；The University of Hong Kong（香港大学）；Monash University（莫纳什大学）；Temple University（天普大学）；Peng Cheng Laboratory（鹏城实验室）
