BestHub
Sign in
Tagged articles
14 articles
Page 1 of 1
DeepHub IMBA
DeepHub IMBA
Mar 23, 2026 · Artificial Intelligence

How KgCoOp Uses Knowledge‑Guided Context Optimization to Prevent Prompt Tuning Forgetting

The article analyzes why standard prompt tuning (CoOp) causes catastrophic forgetting in visual‑language models, introduces the KgCoOp framework that adds a knowledge‑guided loss to regularize prompts, and shows through extensive experiments on 11 benchmarks that KgCoOp improves unseen‑class accuracy, harmonic mean, and efficiency while discussing trade‑offs and limitations.

Catastrophic ForgettingKnowledge-guided OptimizationPrompt Tuning
0 likes · 11 min read
How KgCoOp Uses Knowledge‑Guided Context Optimization to Prevent Prompt Tuning Forgetting
AI Insight Log
AI Insight Log
Jan 1, 2026 · Artificial Intelligence

Can DeepSeek’s mHC Architecture Break ResNet’s Decade-Long Dominance?

DeepSeek’s new paper “mHC: Manifold‑Constrained Hyper‑Connections” proposes a novel architecture that replaces traditional residual connections with mathematically constrained hyper‑connections, showing on a 27B model a modest 6.7 % training‑time increase but significant stability gains and superior performance on BBH, DROP and GSM8K benchmarks.

DeepSeekLLM trainingResNet
0 likes · 8 min read
Can DeepSeek’s mHC Architecture Break ResNet’s Decade-Long Dominance?
IT Services Circle
IT Services Circle
May 2, 2025 · Artificial Intelligence

Understanding Gradient Vanishing in Deep Neural Networks and How to Mitigate It

The article explains why deep networks suffer from gradient vanishing—especially when using sigmoid or tanh activations—covers the underlying mathematics, compares activation functions, and presents practical techniques such as proper weight initialization, batch normalization, residual connections, and code examples to visualize the phenomenon.

Batch NormalizationDeep LearningNeural Networks
0 likes · 7 min read
Understanding Gradient Vanishing in Deep Neural Networks and How to Mitigate It
Bilibili Tech
Bilibili Tech
Aug 27, 2024 · Artificial Intelligence

Multimodal Video Scene Classification for Adaptive Video Processing

The paper presents a multimodal video scene classification system that leverages CLIP‑generated pseudo‑labels and a fine‑tuned image encoder to automatically identify nature, animation/game, and document scenes, enabling more effective adaptive transcoding, intelligent restoration, and quality assessment for user‑generated content on platforms such as Bilibili.

Bilibili multimediaCLIPComputer Vision
0 likes · 17 min read
Multimodal Video Scene Classification for Adaptive Video Processing
Baobao Algorithm Notes
Baobao Algorithm Notes
Apr 11, 2022 · Artificial Intelligence

Can ResNet Still Beat Transformers? A Deep Dive into Modern Training Tricks

This article reviews recent research and official PyTorch blog updates that modify ResNet architectures and training tricks, compares their performance against EfficientNet, ConvNeXt, and Vision Transformers using extensive ImageNet benchmarks, and provides both literature‑based and local evaluation results to assess whether classic CNNs remain competitive.

CNNResNetVision Transformer
0 likes · 13 min read
Can ResNet Still Beat Transformers? A Deep Dive into Modern Training Tricks
Code DAO
Code DAO
Dec 29, 2021 · Artificial Intelligence

Understanding Stand-Alone Axial-Attention for Panoptic Segmentation

The paper proposes a stand‑alone axial‑attention mechanism that converts 2‑D attention into 1‑D to lower computational cost while preserving global context, introduces position‑sensitive self‑attention, integrates it into Axial‑ResNet and Axial‑DeepLab, and demonstrates strong results on four large segmentation datasets.

Axial AttentionComputer VisionDeepLab
0 likes · 7 min read
Understanding Stand-Alone Axial-Attention for Panoptic Segmentation
Code DAO
Code DAO
Dec 22, 2021 · Artificial Intelligence

Understanding SimCLR: A Simple Contrastive Learning Framework for Visual Representations

This article explains SimCLR, the 2020 Google Research framework that advances self‑supervised visual pre‑training by using extensive data augmentations, a ResNet encoder, a projection‑head MLP, and the NT‑Xent loss to learn robust image representations that outperform many prior methods on ImageNet and other benchmarks.

Computer VisionNT-Xent lossResNet
0 likes · 7 min read
Understanding SimCLR: A Simple Contrastive Learning Framework for Visual Representations
Python Programming Learning Circle
Python Programming Learning Circle
Jul 6, 2021 · Artificial Intelligence

Understanding ResNet and Building It from Scratch with PyTorch

This article explains the motivation behind residual networks, describes the architecture of ResNet including residual blocks and skip connections, lists available Keras implementations, and provides a step‑by‑step PyTorch tutorial with complete code to construct and test ResNet‑50/101/152 models.

CNNDeep LearningPyTorch
0 likes · 10 min read
Understanding ResNet and Building It from Scratch with PyTorch
58 Tech
58 Tech
Oct 14, 2019 · Artificial Intelligence

Advertisement Image Recognition System for 58.com: Design, Implementation, and Performance

This article describes 58.com’s deep‑learning‑based advertisement image recognition platform, covering its background, system architecture, QR‑code detection, multi‑scale ResNet classification, category fusion, performance metrics, real‑world case studies, and online service statistics.

58.comContent SecurityDeep Learning
0 likes · 9 min read
Advertisement Image Recognition System for 58.com: Design, Implementation, and Performance
Hulu Beijing
Hulu Beijing
Mar 7, 2019 · Artificial Intelligence

From AlexNet to ResNeXt: Key Milestones in CNN Evolution

This article traces the evolution of convolutional neural networks from the pioneering AlexNet through VGG, Inception, ResNet, Inception‑v4, Inception‑ResNet and ResNeXt, highlighting architectural innovations, performance gains, and the underlying biological inspirations that shaped modern deep learning models.

AlexNetCNNComputer Vision
0 likes · 13 min read
From AlexNet to ResNeXt: Key Milestones in CNN Evolution
Alibaba Cloud Developer
Alibaba Cloud Developer
Sep 6, 2018 · Artificial Intelligence

How Wide‑ResNet with Batch Norm Boosts 1688’s ‘You May Like’

This article introduces the Wide&Deep, PNN, DeepFM, and a novel Wide‑ResNet model applied to Alibaba’s 1688 “You May Like” recommendation, describes the system architecture, training data, experimental results showing AUC improvements with batch normalization, and shares practical tuning insights.

Batch NormalizationResNetdeepfm
0 likes · 12 min read
How Wide‑ResNet with Batch Norm Boosts 1688’s ‘You May Like’
Qunar Tech Salon
Qunar Tech Salon
Aug 19, 2016 · Artificial Intelligence

Deep Learning Anti‑Scam Guide: A Non‑Technical Overview of Neural Networks, Training, and Practical Tips

This article provides a humorous yet informative, non‑mathematical guide to deep learning, covering neural network basics, layer addition, training methods, back‑propagation, unsupervised pre‑training, regularization, ResNet shortcuts, GPU computation, framework choices, and practical advice for applying deep learning to industrial data.

AIDeep LearningGPU
0 likes · 26 min read
Deep Learning Anti‑Scam Guide: A Non‑Technical Overview of Neural Networks, Training, and Practical Tips