channel-attention

Source code for AAAI 2020 paper "Channel Attention Is All You Need for Video Frame Interpolation"

[ICCV 2021] Official Pytorch implementation for Discriminative Region-based Multi-Label Zero-Shot Learning SOTA results on NUS-WIDE and OpenImages

Image Super-Resolution Using Very Deep Residual Channel Attention Networks Implementation in Tensorflow

This repo contains the 3D implementation of the commonly used attention mechanism for imaging.

Gluon implementation of channel-attention modules: SE, ECA, GCT

C3Net: Demoireing Network Attentive in Channel, Color and Concatenation (CVPRW 2020)

Unlock the potential of latent diffusion models with MNIST! 🚀 Dive into reconstructing and generating digits using cutting-edge techniques like Autoencoders with Channel Attention Blocks and DDPMs. Perfect for enthusiasts of computer vision, deep learning, and generative modeling! 🌌✨

This work proposes a feature refined end-to-end object tracking framework with a balanced performance using a high-level feature refine tracking framework. The feature refine module enhances the target feature representation power that allows the network to capture salient information to locate the target.

Siamese Attention Learning Framework for Visual Object Tracking

The open source code for the paper "Block Attention and Switchable Normalization based Deep Learning Framework for Segmentation of Retinal Vessels"

ChurnNet: Deep Learning Enhanced Customer Churn Prediction in Telecommunication Industry

This repo contains the 3D implementation of the commonly used attention mechanism for imaging.

Modular PyTorch implementations of popular attention mechanisms (SE, CBAM, ECA, CA, BAM, SimAM, and more) designed for easy integration into any CNN or Transformer model.

Implementation of various channel-wise attention modules

A bifurcated auto-encoder based on channel-wise and spatial-wise attention mechanism with synthetically generated data for segmentation of covid-19 infected regions in CT images

End-to-end implementation of "CephLD-CCA: Cephalometric Landmark Detection with Cartesian Coordinate Channel Attention", released for reproducibility and reusability

We introduce Prompt-Conditioned Channel Attention (PCCA), which deeply integrates spatial prompts by hierarchically modulating channel features throughout the network. Built on PCCA, PROMISE-Net consistently improves segmentation across multiple datasets and architectures, demonstrating a scalable and general prompt-aware framework.

Hint based Image Colorization ConvNet Challenge 2022 in Computer Vision from Prof. YJ Jung in Gachon Univ

This is the official implementation of DA-DMD model.