ImageNet
PulseAugur coverage of ImageNet — every cluster mentioning ImageNet across labs, papers, and developer communities, ranked by signal.
- used by CIFAR-10 70%
- used by Diffusion Models 70%
- instance of Diffusion Models 70%
- used by vision transformer 70%
- used by residual neural network 70%
- instance of Diffusion models of ion-channel gating and the origin of power-law distributions from single-channel recording 70%
- instance of magazine 70%
- used by ConvNeXt 70%
- instance of arXiv 60%
- instance of CIFAR-100 60%
- instance of CNNS 60%
- affiliated with arXiv 50%
13 天有情绪数据
-
TwistNet-2D learns second-order channel interactions for texture recognition
Researchers have developed TwistNet-2D, a novel module designed to enhance texture recognition by capturing second-order channel interactions. This module computes local pairwise channel products with directional spatia…
-
Researchers propose new metrics to evaluate AI explainability methods
Researchers have developed a new method to evaluate explainability techniques for Convolutional Neural Networks (CNNs), addressing the lack of robust metrics beyond Intersection over Union (IoU). The study proposes usin…
-
Researchers develop DUNE, a dual-branch method to create robust unlearnable examples for AI models.
Researchers have developed DUNE, a novel dual-branch approach to create robust unlearnable examples for AI model training. This method optimizes perturbations in both spatial and color domains to degrade model generaliz…
-
New methods enhance autoregressive visual generation with prologue tokens and implicit modeling
Researchers have introduced two novel approaches to enhance autoregressive visual generation models. The first, called Prologue, addresses the reconstruction-generation gap by prepending a small set of prologue tokens t…
-
深度学习模型在从图表数据预测加密货币状态方面显示出潜力
研究人员对使用深度学习基于视觉图表表示进行加密货币状态预测进行了系统性研究。他们比较了各种图像编码方法、图表组件和神经网络架构，包括 CNN、ResNet18、EfficientNet-B0 和 Vision Transformers。研究发现，应用于原始蜡烛图的简单 4 层 CNN 达到了 0.892 的高 AUC-ROC，优于更复杂的预训练模型，并且更简单的表示方法出奇地更有效。
-
Apple advances normalizing flows, researchers explore denoising and state estimation
Apple Machine Learning Research has introduced iTARFlow, an advancement in Normalizing Flow generative models that maintains a likelihood-based objective and uses an iterative denoising procedure for sampling. This meth…
-
Researchers question 'real' image definition amid deepfake concerns
A new position paper argues that the current focus on detecting AI-generated "fake" images is misguided. The authors contend that the definition of a "real" image needs re-evaluation, as modern smartphone cameras use co…
-
GPT-4o and other multimodal models evaluated on computer vision tasks
A new paper evaluates how well multimodal foundation models, including GPT-4o and Gemini 1.5 Pro, perform on standard computer vision tasks. Researchers developed a prompt-chaining method to translate vision tasks into …
-
Video Generation with Predictive Latents
Researchers have developed several new methods to improve the efficiency and quality of visual generative models. DC-DiT introduces dynamic chunking to Diffusion Transformers, adaptively compressing visual data for fast…
-
OpenAI-affiliated researchers integrate FID into training, achieving sub-0.8 ImageNet scores
Researchers from USC, CMU, CUHK, and OpenAI have developed a new method called FD-loss that allows the Fréchet Inception Distance (FID) metric to be directly incorporated into the training process of image generation mo…
-
Flow Matching research advances efficiency, control, and applications
Recent research explores advancements in Flow Matching, a generative modeling technique. Several papers introduce new methods to improve its efficiency, controllability, and applicability to diverse data types. Innovati…
-
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
Researchers have developed an end-to-end training pipeline for autoregressive image generation that jointly optimizes reconstruction and generation. This approach allows for direct supervision of the visual tokenizer fr…
-
Researchers propose FD-loss to optimize visual generation in representation space
Researchers have introduced a new training objective called FD-loss, which optimizes the Fréchet Distance (FD) in representation spaces for visual generation. This method decouples the population size for FD estimation …
-
Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs
Researchers have developed a novel 'Online Architecture' strategy for Convolutional Neural Networks (CNNs) that significantly enhances translation invariance. By strategically inserting Global Average Pooling (GAP) laye…
-
新的预训练策略提高了遥感图像分割中深度学习的准确性
研究人员为用于遥感图像语义分割的深度学习模型开发了一种新的预训练策略。该方法旨在减轻由ImageNet等通用图像数据集与专业遥感数据之间的域差异引起的性能下降。通过指导模型在预训练期间避免学习特定于域的特征，该策略增强了泛化能力。该方法在iSAID、MFNet、PST900和Potsdam等四个不同数据集上取得了最先进的结果，为计算机视觉和遥感领域的统一基础模型铺平了道路。
-
QB-LIF neuron boosts SNN efficiency with learnable scale and burst spiking
Researchers have introduced QB-LIF, a novel neuron model for spiking neural networks (SNNs) that addresses the information throughput limitations of binary spike coding. QB-LIF reformulates burst spiking using a learnab…
-
DINOv3 improves chest radiograph classification at higher resolutions
A new study published on arXiv investigates the effectiveness of DINOv3, a self-supervised learning model, for classifying chest radiographs. Researchers found that while DINOv3 did not consistently outperform its prede…
-
DynProto method dynamically learns OOD prototypes for improved vision-language model detection
Researchers have introduced DynProto, a new method for detecting out-of-distribution (OOD) samples in vision-language models. Unlike previous approaches that rely on predefined OOD labels, DynProto dynamically learns OO…
-
Laplace-Bridged Smoothing offers faster, certified AI robustness on edge devices
Researchers have developed Laplace-Bridged Smoothing (LBS), a new method to improve the efficiency and effectiveness of certified robustness for machine learning models. LBS analytically reformulates Randomized Smoothin…
-
New Noise-Based Spectral Embedding method efficiently selects features for AI models
Researchers have introduced Noise-Based Spectral Embedding (NBSE), a novel physics-informed method for feature selection in high-dimensional datasets. This technique avoids greedy search by constructing a similarity gra…