https://github.com/ChenJoya/dropit
공식 코드DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training
Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms
QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes
Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation
Pluggable Style Representation Learning for Multi-Style Transfer
SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer
DualConv: Dual Convolutional Kernels for Lightweight Deep Neural Networks
Structure-Aware Completion of Photogrammetric Meshes in Urban Road Environment
MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation
Cross-domain Detection via Graph-induced Prototype Alignment
Cervical Glandular Cell Detection from Whole Slide Image with Out-Of-Distribution Data
Deep Learning-Based Quantification of Pulmonary Hemosiderophages in Cytology Slides
Attention-Based Transformers for Instance Segmentation of Cells in Microstructures
PDNet: Prior-model Guided Depth-enhanced Network for Salient Object Detection
Distributed Intelligent Video Surveillance for Early Armed Robbery Detection based on Deep Learning
A Comparison of Named Entity Recognition Tools Applied to Biographical Texts
Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models
Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection
You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery
Text Annotation Graphs: Annotating Complex Natural Language Phenomena
Adaptive Low Rank Adaptation of Segment Anything to Salient Object Detection
A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications
CSL-YOLO: A New Lightweight Object Detection System for Edge Computing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.