ICLR 2022
VICReg: Self-Supervised Learning Without Collapse
Adrien Bardes, Jean Ponce, +1
How variance, invariance, and covariance regularization enables self-supervised representation learning without negative pairs or momentum encoders.
ML Paper Reviews - Page 5
Expert analysis and in-depth reviews of machine learning research papers. Covering computer vision, deep learning, and AI innovations with practical insights.
- 54 papers
- 105 topics
- 2006-2026 publication years
Paper Reviews - Page 5
NeurIPS 2023
Visual Instruction Tuning
Haotian Liu, Chunyuan Li, +2
LLaVA paper: align LLMs with visual information through instruction tuning on image-text pairs, enabling multimodal understanding and reasoning.
ECCV 2022
Plain ViT Backbones for Object Detection
Yanghao Li, Hanzi Mao, +2
Investigating the effectiveness of plain Vision Transformers as backbones for object detection and proposing modifications to improve their performance.
- Transformers
- Computer Vision
- Object Detection
- +1 more tags
CVPR 2016
You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon, Santosh Divvala, +2
Introducing YOLO, a unified, real-time object detection system that frames object detection as a single regression problem.
- Object Detection
- Computer Vision
- Deep Learning
- +2 more tags
ICML 2019
EfficientNet: Compound Scaling for CNNs
Mingxing Tan, Quoc V. Le
EfficientNet achieves state-of-the-art image classification accuracy with improved efficiency through a novel compound scaling method for CNNs.
NeurIPS 2015
Faster R-CNN: Real-Time Object Detection
Shaoqing Ren, Kaiming He, +2
Faster R-CNN explained: how Region Proposal Networks (RPN) enable near real-time object detection with shared convolutional features.
- Object Detection
- Computer Vision
- Deep Learning
- +3 more tags
2023
Segment Anything Model (SAM)
Alexander Kirillov, Eric Mintun, +3
SAM is a promptable segmentation model that can segment any object in an image using points, boxes, or text prompts with zero-shot generalization.
- Computer Vision
- Image Segmentation
- Deep Learning
- +3 more tags
ICML 2023
BLIP-2: Efficient Vision-Language Pre-training
Junnan Li, Dongxu Li, +2
BLIP-2 leverages frozen image encoders and LLMs for efficient vision-language pre-training, achieving state-of-the-art multimodal performance.
2020
End-to-End Object Detection with Transformers
Nicolas Carion, Francisco Massa, +4
Introducing DETR, a novel end-to-end object detection framework that leverages Transformers to directly predict a set of object bounding boxes.
- Transformers
- Computer Vision
- Object Detection
- +2 more tags
Showing 37-45 of 54 papers