2023
Visual Instruction Tuning
LLaVA paper: align LLMs with visual information through instruction tuning on image-text pairs, enabling multimodal understanding and reasoning.
Tagged with
computer vision
Explore machine learning papers and reviews related to computer vision. Find insights, analysis, and implementation details.
13
Papers Found
Papers Related to computer vision
2022
Plain ViT Backbones for Object Detection
Investigating the effectiveness of plain Vision Transformers as backbones for object detection and proposing modifications to improve their performance.
2016
You Only Look Once: Unified, Real-Time Object Detection
Introducing YOLO, a unified, real-time object detection system that frames object detection as a single regression problem.
2019
EfficientNet: Compound Scaling for CNNs
EfficientNet achieves state-of-the-art image classification accuracy with improved efficiency through a novel compound scaling method for CNNs.
2015
Faster R-CNN: Real-Time Object Detection
Faster R-CNN explained: how Region Proposal Networks (RPN) enable near real-time object detection with shared convolutional features.
2023
Segment Anything Model (SAM)
SAM is a promptable segmentation model that can segment any object in an image using points, boxes, or text prompts with zero-shot generalization.
2020
End-to-End Object Detection with Transformers
Introducing DETR, a novel end-to-end object detection framework that leverages Transformers to directly predict a set of object bounding boxes.
2023
BLIP-2: Efficient Vision-Language Pre-training
Computer VisionNatural Language ProcessingDeep LearningMultimodal LearningBLIP-2Vision-Language Models
BLIP-2 leverages frozen image encoders and LLMs for efficient vision-language pre-training, achieving state-of-the-art multimodal performance.
2021
ViT: An Image is Worth 16x16 Words
Vision Transformer (ViT) explained: how splitting images into 16x16 patches enables pure transformer architecture for state-of-the-art image recognition.
2006
SURF: Speeded Up Robust Features
SURF is a fast and robust algorithm for local feature detection and description, used in object recognition, image registration, and 3D reconstruction.
2021
Swin Transformer: Hierarchical ViT with Shifted Windows
Swin Transformer: hierarchical Vision Transformer using shifted windows for efficient image classification, object detection, and segmentation.
2021
CLIP: Visual Models via Language Supervision
CLIP explained: contrastive learning on 400M image-text pairs enables zero-shot image classification and powerful vision-language understanding.
2016
Deep Residual Learning for Image Recognition
ResNet analysis: how skip connections and residual learning solved the degradation problem, enabling training of 100+ layer neural networks.