CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples
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.
Code (5)
Tasks
Image RetrievalRetrievalSimilar Papers 제목 키워드 기반
Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval
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 RetrievalRetrievalRetrieve in Style: Unsupervised Facial Feature Transfer and Retrieval
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…
DisentanglementRetrievalBoot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval
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 RetrievalRetrievalFine-Tuning StyleGAN2 For Cartoon Face Generation
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 TranslationTranslationFine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs
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