Mining Transformer

Mining Transformer research focuses on improving the efficiency and accuracy of image segmentation and classification tasks, particularly in scenarios with limited training data (few-shot learning). Current efforts center on developing transformer-based architectures that effectively mine relevant information from both support (example) and query (target) images, often employing adversarial training or iterative prototype refinement to bridge the gap between them. These advancements are significant for applications like medical image analysis (e.g., skin lesion classification) and co-salient object detection, where accurate and efficient algorithms are crucial for improved diagnostic capabilities and automated image processing.

Papers

October 12, 2024

Token Pruning using a Lightweight Background Aware Vision Transformer
Sudhakar Sah, Ravish Kumar, Honnesh Rohmetra, Ehsan Saboori
Vision Transformer Object Detector Token Pruning Transformer Training Mining Transformer

November 29, 2023

Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation
Yuan Wang, Naisong Luo, Tianzhu Zhang
Segmentation Based Approach Query Information Shot Segmentation Human Driving Focus Transformer Based Generative Adversarial Query Image Segmentation Mining Transformer

April 30, 2023

Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection
Long Li, Junwei Han, Ni Zhang, Nian Liu, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan
Co Salient Object Detection Co Saliency Mining Transformer

February 2, 2023

LesionAid: Vision Transformers-based Skin Lesion Generation and Classification
Ghanta Sai Krishna, Kundrapu Supriya, Mallikharjuna Rao K, Meetiksha Sorgile
Classification Code Transformer Based Vision Paper Skin Lesion Skin Cancer ViT Model Lesion Wise Metric Mining Transformer

October 13, 2022

Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
Yuanwei Liu, Nian Liu, Xiwen Yao, Junwei Han
Semantic Segmentation COCO Dataset Shot Semantic Segmentation Category Learning Mining Transformer

Mining Transformer

Papers

Token Pruning using a Lightweight Background Aware Vision Transformer

Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation

Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection

LesionAid: Vision Transformers-based Skin Lesion Generation and Classification

Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation