晓飞的算法工程笔记

论文: Semantic Enhanced Few-shot Object Detection 论文地址：https://arxiv.org/abs/2406.13498 ...

论文: Strengthening Layer Interaction via Dynamic Layer Attention 论文地址：https://arxiv.org...

论文: Small Scale Data-Free Knowledge Distillation 论文地址：https://arxiv.org/abs/2406.07876...

论文: Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classif...

论文: A Spitting Image: Modular Superpixel Tokenization in Vision Transformers 论文地址：http...

论文: Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning...

论文: Fine-grained Classes and How to Find Them 论文地址：https://arxiv.org/abs/2406.11070 代码...

论文: KernelWarehouse: Rethinking the Design of Dynamic Convolution 论文地址：https://arxiv.o...

论文: Efficient and Versatile Robust Fine-Tuning of Zero-shot Models 论文地址：https://www.ar...

论文: CamoTeacher: Dual-Rotation Consistency Learning for Semi-Supervised Camouflaged Ob...

论文: OVMR: Open-Vocabulary Recognition with Multi-Modal References 论文地址：https://arxiv.o...

论文: Scaling Backwards: Minimal Synthetic Pre-training? 论文地址：https://arxiv.org/abs/2408...

论文: MovieSum: An Abstractive Summarization Dataset for Movie Screenplays 论文地址：https://...

论文: Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Ap...

论文: You Only Look at One Sequence: Rethinking Transformer in Vision through Object Det...

论文: You Only Need Less Attention at Each Stage in Vision Transformers 论文地址：https://arx...

论文: Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with ...

论文: POA: Pre-training Once for Models of All Sizes 论文地址：https://arxiv.org/abs/2408.010...

论文: Towards Reliable Advertising Image Generation Using Human Feedback 论文地址：https://ar...

论文: Accelerating Image Super-Resolution Networks with Pixel-Level Classification 论文地址：...