Learning Transferable Visual Models From Natural Language Supervision
CLIP learns from image-caption pairs to recognize categories described in words.
2021
77,118
Works
Selected research papers and books, linked to their authors.
Going Deeper with Convolutions
GoogLeNet recognizes images with parallel filters operating at different scales.
2015
75,185
ImageNet Large Scale Visual Recognition Challenge
Documented ImageNet's shared tests and progress in recognizing and locating objects in images.
2015
57,636
Focal Loss for Dense Object Detection
Focal loss shifts object-detector training toward difficult examples rather than easy ones.
2017
55,935
Mask R-CNN
Mask R-CNN identifies objects and traces each one's outline in an image.
2017
53,860
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
R-CNN identifies objects by applying neural networks to candidate image regions.
2014
52,204
SURF: Speeded Up Robust Features
SURF quickly finds and matches image details despite changes in scale or rotation.
2006
41,701
High-Resolution Image Synthesis with Latent Diffusion Models
Made diffusion image generation more efficient by working with compressed image representations.
2022
41,197
Segment Anything
SAM outlines objects in images in response to prompts such as clicks or boxes.
2023
26,160
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
NeRF learns a 3D scene from photos to render it from new viewpoints.
2020
22,632