https://github.com/scabini/RADAM
공식 코드RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps
GOLLuM: Gaussian Process Optimized LLMs -- Reframing LLM Finetuning through Bayesian Optimization
Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More
MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation
Evaluation of Multi-indicator And Multi-organ Medical Image Segmentation Models
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture
On Recurrent Neural Networks for Sequence-based Processing in Communications
Urban Change Detection Using a Dual-Task Siamese Network and Semi-Supervised Learning
Real Time Trajectory Prediction Using Deep Conditional Generative Models
TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation
HyperLips: Hyper Control Lips with High Resolution Decoder for Talking Face Generation
Finetuning Pretrained Transformers into Variational Autoencoders
ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences
ABCD: A Graph Framework to Convert Complex Sentences to a Covering Set of Simple Sentences
VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting
Context-Based Trit-Plane Coding for Progressive Image Compression
Numerical Weather Forecasting using Convolutional-LSTM with Attention and Context Matcher Mechanisms
SepMark: Deep Separable Watermarking for Unified Source Tracing and Deepfake Detection
Neural Machine Translation System of Indic Languages -- An Attention based Approach
Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task
Efficient Context-Aware Network for Abdominal Multi-organ Segmentation
Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.