CNN Backbone

A CNN backbone refers to the foundational convolutional neural network architecture used for feature extraction in various computer vision tasks. Current research focuses on improving efficiency (e.g., through structured pruning), enhancing robustness (e.g., by incorporating rotation invariance), and adapting backbones for specific applications (e.g., lifelong learning, multi-label classification). These advancements are crucial for optimizing resource consumption in embedded systems and improving accuracy across diverse domains, impacting fields like robotics, medical image analysis, and remote sensing.

Papers

September 12, 2024

Structured Pruning for Efficient Visual Place Recognition
Oliver Grainge, Michael Milford, Indu Bodala, Sarvapali D. Ramchurn, Shoaib Ehsan
Place Recognition Visual Place Recognition Structured Pruning Global Re Localization CNN Backbone Bounded Recall

April 17, 2024

Achieving Rotation Invariance in Convolution Operations: Shifting from Data-Driven to Mechanism-Assured
Hanlin Mo, Guoying Zhao
Data Driven Convolution Operation Rotation Invariant Rotation Invariance CNN Backbone

March 31, 2024

Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalization
Mainak Singha, Ankit Jha, Shirsha Bose, Ashwin Nair, Moloud Abdar, Biplab Banerjee
Full Potential Single CLIP Domain Adaptive CNN Backbone Open Domain Generalization

March 24, 2024

Diverse Representation Embedding for Lifelong Person Re-Identification
Shiben Liu, Huijie Fan, Qiang Wang, Xiai Chen, Zhi Han, Yandong Tang
Person Re Identification Representation Alignment CNN Backbone Diverse Feature Representation Diversity Diverse Representation

November 30, 2023

Perceptual Group Tokenizer: Building Perception with Iterative Grouping
Zhiwei Deng, Ting Chen, Yang Li
Self Supervised Representation Learning CNN Backbone Perceptual Grouping Indoor Body Perception

November 29, 2023

CRAFT: Contextual Re-Activation of Filters for face recognition Training
Aman Bhatta, Domingo Mery, Haiyu Wu, Kevin W. Bowyer
Face Recognition Convolutional Filter Activation Map Max Filter Traditional CrAFT CNN Backbone

October 25, 2023

Deep Learning for Plant Identification and Disease Classification from Leaf Images: Multi-prediction Approaches
Jianping Yao, Son N. Tran, Saurabh Garg, Samantha Sawyer
Deep Learning Convolutional Neural Network Disease Classification Plant Identification CNN Backbone Leaf Image

July 1, 2023

WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting
Pranav Jeevan, Dharshan Sampath Kumar, Amit Sethi
Vision Transformer Self Supervised Convolutional Layer CNN Backbone Token Mixing

January 18, 2023

Model-based inexact graph matching on top of CNNs for semantic scene understanding
Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère, Rozenn Dahyot, Isabelle Bloch
Semantic Segmentation CNN Model Segmentation Result Semantic Scene Brain Segmentation Uncertainty Aware Graph CNN Backbone TOp Front TopMost Deep Bayesian Segmentation

July 8, 2022

Learning Sequential Descriptors for Sequence-based Visual Place Recognition
Riccardo Mereu, Gabriele Trivigno, Gabriele Berton, Carlo Masone, Barbara Caputo
Visual Place Recognition Aware Aggregator CNN Backbone Sequential Classifier

June 9, 2022

SwinCheX: Multi-label classification on chest X-ray images with transformers
Sina Taslimi, Soroush Taslimi, Nima Fathi, Mohammadreza Salehi, Mohammad Hossein Rohban
Deep Neural Network Transformer Megatron Decepticons Deep Model Multi Label Classification Chest X Ray Image CNN Backbone

April 14, 2022

3D Shuffle-Mixer: An Efficient Context-Aware Vision Learner of Transformer-MLP Paradigm for Dense Prediction in Medical Volume
Jianye Pang, Cheng Jiang, Yihao Chen, Jianbo Chang, Ming Feng, Renzhi Wang, Jianhua Yao
Vision Transformer Dense Prediction Deep Transformer Local Transformer Visual in Context Learning MRI Volume CNN Backbone

April 11, 2022

Self-supervised Vision Transformers for Joint SAR-optical Representation Learning
Yi Wang, Conrad M Albrecht, Xiao Xiang Zhu
Vision Transformer Self Supervised Self Supervised Vision Transformer CNN Backbone SAR to Optical

February 1, 2022

Advances in MetaDL: AAAI 2021 challenge and workshop
Adrian El Baz, Isabelle Guyon, Zhengying Liu, Jan van Rijn, Sebastien Treguer, Joaquin Vanschoren
Deep Learning Shot Learning Challenge Task Meta Training CNN Backbone Auto Assembling Ai Metalearning Algorithm

December 9, 2021

PE-former: Pose Estimation Transformer
Paschalis Panteleris, Antonis Argyros
Encoder Decoder Vision Transformer Architecture Convolutional Backbone X Former Pure Transformer CNN Backbone Pose Induced Video Transformer

November 4, 2021

PDBL: Improving Histopathological Tissue Classification with Plug-and-Play Pyramidal Deep-Broad Learning
Jiatai Lin, Guoqiang Han, Xipeng Pan, Hao Chen, Danyi Li, Xiping Jia, Zhenwei Shi, Zhizhen Wang, Yanfen Cui, Haiming Li, Changhong Liang, Li Liang, Zaiyi Liu, Chu Han
CNN Backbone Broad Learning