AlexNet: ImageNet Classification with Deep Convolutional Neural Networks
AlexNet won ImageNet 2012 by a wide margin with GPU-trained deep convolutions, ReLU and dropout — the result that started the deep learning era.
14 reports · 2012–2023
Image classification, detection, segmentation, representation learning and neural scene representations.
AlexNet won ImageNet 2012 by a wide margin with GPU-trained deep convolutions, ReLU and dropout — the result that started the deep learning era.
GoogLeNet won ILSVRC 2014 with Inception modules running multi-scale convolutions in parallel — deeper CNNs with far fewer parameters than rivals.
VGG showed that stacking small 3x3 convolutions into 16-19 layer CNNs wins at ImageNet classification — the simple deep-learning blueprint behind modern vision.
Faster R-CNN made object detection near real-time with Region Proposal Networks sharing CNN features — anchors, RoI pooling and joint training explained.
U-Net's symmetric encoder-decoder with skip connections became the standard for pixel-level prediction, from biomedical imaging to diffusion models.
An AI-generated review of YOLO, the 2015 detector that framed object detection as a single regression problem and made real-time detection possible on a GPU.
Mask R-CNN adds a mask branch and RoIAlign to Faster R-CNN for instance segmentation — pixel-level masks, boxes and classes from one network.
The Vision Transformer applied a plain transformer to image patches and matched CNNs at scale — proving convolutions were optional for recognition.
DETR replaces anchors and NMS with a transformer predicting objects as a set — end-to-end object detection with bipartite matching, explained simply.
An AI-generated review of NeRF, the 2020 method that represents a 3D scene as a neural field and renders photorealistic novel views from sparse input photos.
SimCLR learns visual representations without labels via contrastive learning on augmented image pairs, matching supervised accuracy with linear probes.
An AI-generated review of CLIP, the contrastive vision-language model that made zero-shot image classification and text-guided image understanding practical.
Masked Autoencoders pretrain Vision Transformers by reconstructing 75% masked patches, scaling self-supervised vision with simple asymmetric design.
How the Segment Anything project reframed segmentation as a promptable task and released a 1-billion-mask dataset that made zero-shot segmentation practical.