**Residual Multi-Layer Perceptrons**, or **ResMLP**, is an architecture built entirely upon [multi-layer perceptrons](https://paperswithcode.com/methods/category/feedforward-networks) for image classi

ResMLP

ResMLP: Feedforward networks for image classification with data-efficient training

Internet Explorer explores the web in a self-supervised manner to progressively find relevant examples that improve performance on a desired target dataset. It cycles between searching for images on t

Internet Explorer

Internet Explorer: Targeted Representation Learning on the Open Web

**BIMAN**, or **Bot Identification by commit Message, commit Association, and author Name**, is a technique to detect bots that commit code. It is comprised of three methods that consider independent 

BIMAN

Detecting and Characterizing Bots that Commit Code

**nnFormer**, or **not-another transFormer**, is a semantic segmentation model with an interleaved architecture based on empirical combination of self-attention and [convolution](https://paperswithcod

nnFormer

nnFormer: Interleaved Transformer for Volumetric Segmentation

**Locally-Grouped Self-Attention**, or **LSA**, is a local attention mechanism used in the [Twins-SVT](https://paperswithcode.com/method/twins-svt) architecture. Locally-grouped self-attention (LSA). 

Locally-Grouped Self-Attention

Twins: Revisiting the Design of Spatial Attention in Vision Transformers

**PAFPN** is a feature pyramid module used in Path Aggregation networks ([PANet](https://paperswithcode.com/method/panet)) that combines FPNs with [bottom-up path augmentation](https://paperswithcode.

PAFPN

Path Aggregation Network for Instance Segmentation

**Dynamic R-CNN** is an object detection method that adjusts the label assignment criteria (IoU threshold) and the shape of regression loss function (parameters of Smooth L1 Loss) automatically based 

Dynamic R-CNN

Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training

The core ingredient of **CayleyNet** is a new class of parametric rational complex functions (Cayley polynomials) allowing to efficiently compute spectral filters on graphs that specialize on frequenc

CayleyNet

CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters

**FFB6D** is a full flow bidirectional fusion network for 6D pose estimation of known objects from a single RGBD image. Unlike previous works that extract the RGB and point cloud features independentl

FFB6D

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

**HRank** is a filter pruning method that explores the High Rank of the feature map in each layer (HRank). The proposed HRank  is inspired by the discovery that the average rank of multiple feature ma

HRank

HRank: Filter Pruning using High-Rank Feature Map

A Synaptic Neural Network (SynaNN) consists of synapses and neurons. Inspired by the synapse research of neuroscience, we built a synapse model with a nonlinear and log-concave synapse function of exc

SynaNN

A Synaptic Neural Network and Synapse Learning

**Minimum Description Length** provides a criterion for the selection of models, regardless of their complexity, without the restrictive assumption that the data form a sample from a 'true' distributi

**Gaussian Processes** are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for an unseen point from 

Gaussian Process

**DINO** (self-distillation with no labels) is a self-supervised learning method that directly predicts the output of a teacher network - built with a momentum encoder - using a standard cross-entropy

DINO

Emerging Properties in Self-Supervised Vision Transformers

The **SAGAN Self-Attention Module** is a self-attention module used in the [Self-Attention GAN](https://paperswithcode.com/method/sagan) architecture for image synthesis. In the module, image features

SAGAN Self-Attention Module

Self-Attention Generative Adversarial Networks

SCARF is a simple, widely-applicable technique for contrastive learning, where views are formed by corrupting a random subset of features. When applied to pre-train deep neural networks on the 69 real

SCARF

SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption

GENet combines part gathering and excitation operations. In the first step, it aggregates input features over large neighborhoods and models the relationship between different spatial locations. In th

Gather-Excite Networks

Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks

**Deformable Attention Module** is an attention module used in the [Deformable DETR](https://paperswithcode.com/method/deformable-detr) architecture, which seeks to overcome one issue base [Transforme

Viet-Anh on Software

AI Glossary

Residual Multi-Layer Perceptrons