VGG: Very Deep Convolutional Networks
VGG showed that stacking small 3x3 convolutions into 16-19 layer CNNs wins at ImageNet classification — the simple deep-learning blueprint behind modern vision.
Search across AI research reports and briefs. Results load instantly — no JavaScript required.
22 results for “vision”
VGG showed that stacking small 3x3 convolutions into 16-19 layer CNNs wins at ImageNet classification — the simple deep-learning blueprint behind modern vision.
SimCLR learns visual representations without labels via contrastive learning on augmented image pairs, matching supervised accuracy with linear probes.
Masked Autoencoders pretrain Vision Transformers by reconstructing 75% masked patches, scaling self-supervised vision with simple asymmetric design.
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.
Grad-CAM explains CNN decisions with gradient-weighted heatmaps, revealing which image regions drove each prediction without retraining.
GoogLeNet won ILSVRC 2014 with Inception modules running multi-scale convolutions in parallel — deeper CNNs with far fewer parameters than rivals.
Faster R-CNN made object detection near real-time with Region Proposal Networks sharing CNN features — anchors, RoI pooling and joint training explained.
DETR replaces anchors and NMS with a transformer predicting objects as a set — end-to-end object detection with bipartite matching, explained simply.
Zeiler and Fergus visualized CNN layers with deconvolution, revealing edges, textures and objects emerging layer by layer inside the network.
How the Segment Anything project reframed segmentation as a promptable task and released a 1-billion-mask dataset that made zero-shot segmentation practical.
Whisper trained on 680,000 hours of weakly supervised web audio and showed that scale plus multitask formatting beats hand-curated speech datasets.
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.
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 ResNet, the 2015 architecture that used skip connections to train networks hundreds of layers deep and became the default backbone.
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.
An AI-generated review of DDPM, the 2020 paper that turned diffusion models into the leading family of generative models for images.
An AI-generated review of CLIP, the contrastive vision-language model that made zero-shot image classification and text-guided image understanding practical.
The Vision Transformer applied a plain transformer to image patches and matched CNNs at scale — proving convolutions were optional for recognition.
AlexNet won ImageNet 2012 by a wide margin with GPU-trained deep convolutions, ReLU and dropout — the result that started the deep learning era.
Demonstrates that GPU-trained deep CNNs can dramatically outperform previous approaches on large-scale image classification, catalyzing the modern deep learning era in computer vision.
Trains a shared image-text embedding space with a contrastive objective on 400 million web pairs, enabling zero-shot image classification for any text-defined label set.
Applies a standard transformer encoder directly to image patches; with large-scale pre-training it matches or beats convolutional networks on image classification.