paper-with-me

홈 › Papers

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

2016-04-08 · Filip Radenović, Giorgos Tolias, Ondřej Chum

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task. In this work, we propose to fine-tune CNN for image retrieval from a large collection of unordered images in a fully automated manner. We employ state-of-the-art retrieval and Structure-from-Motion (SfM) methods to obtain 3D models, which are used to guide the selection of the training data for CNN fine-tuning. We show that both hard positive and hard negative examples enhance the final performance in particular object retrieval with compact codes.

📄 PDF Abstract BibTeX arXiv:1604.02426

Code (5)

RuibinMa/comp755project-ruibinma pytorch
filipradenovic/cnnimageretrieval pytorch
filipradenovic/cnnimageretrieval-pytorch pytorch
raojay7/cnnimageretrieval-pytorch pytorch
tuananh1007/CNN-Image-Retrieval-in-PyTorch pytorch

Tasks

Image RetrievalRetrieval

Similar Papers 제목 키워드 기반

Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval

2021-08-12 · ACL 2022 5 · Luyu Gao, Jamie Callan

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to re…

Language ModelingLanguage ModellingPassage RetrievalRetrieval

Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval

2021-07-13 · ICCV 2021 10 · Min Jin Chong, Wen-Sheng Chu, Abhishek Kumar, David Forsyth

We present Retrieve in Style (RIS), an unsupervised framework for facial feature transfer and retrieval on real images. Recent work shows capabilities of transferring local facial features by capitalizing on the disentan…

DisentanglementRetrieval

Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval

2023-11-27 · Fan Jiang, Qiongkai Xu, Tom Drummond, Trevor Cohn

Neural 'dense' retrieval models are state of the art for many datasets, however these models often exhibit limited domain transfer ability. Existing approaches to adaptation are unwieldy, such as requiring explicit super…

Passage RetrievalRetrieval

Fine-Tuning StyleGAN2 For Cartoon Face Generation

2021-06-22 · Jihye Back

Recent studies have shown remarkable success in the unsupervised image to image (I2I) translation. However, due to the imbalance in the data, learning joint distribution for various domains is still very challenging. Alt…

Face GenerationImage-to-Image TranslationTranslation

Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs

2023-12-10 · Oded Ovadia, Menachem Brief, Moshik Mishaeli, Oren Elisha

Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights, as evidenced by their ability to answer diverse questions across different domains. However, this knowledge …

RAGRetrievalRetrieval-augmented Generation