딥러닝 공부방

A Simple Baseline for Zero-Shot Semantic Segmentation with Pre-trained Vision-language Model https://arxiv.org/pdf/2112.14757.pdf CLIP을 zero-shot semantic segmentation에 적용한 논문. MaskFormer로 binary mask를 생성하고 생성한 mask에 대해 mask classification으로 prediction을 수행한다. classifier의 weight를 CLIP의 pre-trained text representation로 사용. 따라서 unseen으로 zero-shot이 가능하다.

Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks https://arxiv.org/abs/2006.07322 Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks Modern neural architectures for classification tasks are trained using the cross-entropy loss, which is widely believed to be empirically superior to the square lo..

Learning to Compare: Relation Network for Few-Shot Learning https://arxiv.org/abs/1711.06025 Learning to Compare: Relation Network for Few-Shot Learning We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-en..

https://arxiv.org/abs/2107.13807 FREE: Feature Refinement for Generalized Zero-Shot Learning Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts dedicated to overcoming the problems of visual-semantic domain gap and seen-unseen bias. However, most existing methods directly use feature extraction models traine arxiv.org FREE, Feature Refinement for Generaliz..

Dense Contrastive Learning for Self-Supervised Visual Pre-Training https://arxiv.org/abs/2011.09157 Dense Contrastive Learning for Self-Supervised Visual Pre-Training To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level predicti..

Task-Indenpendent Knowledge Makes for Transferable Represenations for Generalized Zero-Shot Learning https://arxiv.org/abs/2104.01832 Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning Generalized Zero-Shot Learning (GZSL) targets recognizing new categories by learning transferable image representations. Existing methods find that, by aligning im..

Zero-Shot Learning via Contrastive Learning on Dual Knowledge Graphs https://ieeexplore.ieee.org/document/9607851 Zero-Shot Learning via Contrastive Learning on Dual Knowledge Graphs Graph Convolutional Networks (GCNs), which can integrate both explicit knowledge and implicit knowledge together, have shown effectively for zero-shot learning problems. Previous GCN-based methods generally leverage..

Isometric Propagation Network for Generalized Zero-Shot Learning https://arxiv.org/abs/2102.02038 Isometric Propagation Network for Generalized Zero-shot Learning Zero-shot learning (ZSL) aims to classify images of an unseen class only based on a few attributes describing that class but no access to any training sample. A popular strategy is to learn a mapping between the semantic space of class..

Convolutional Prototype Learning for Zero-Shot Recognition(2019) https://arxiv.org/abs/1910.09728 Convolutional Prototype Learning for Zero-Shot Recognition Zero-shot learning (ZSL) has received increasing attention in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. The key to ZSL is to transfer knowledge from the seen to the unseen classes v..

Class-Prototype Discriminative Network for Generalized Zero-Shot Learning https://ieeexplore.ieee.org/abstract/document/8966463 Class-Prototype Discriminative Network for Generalized Zero-Shot Learning We present a novel end-to-end deep metric learning model named Class-Prototype Discriminative Network (CPDN) for Generalized Zero-Shot Learning (GZSL). It consists of a generative network for prod..