paper-with-me

Papers

End-to-end Binary Representation Learning via Direct Binary Embedding

2017-03-15 · Liu Liu, Alireza Rahimpour, Ali Taalimi, Hairong Qi

Learning binary representation is essential to large-scale computer vision tasks. Most existing algorithms require a separate quantization constraint to learn effective hashing functions. In this work, we present Direct Binary Embedding (DBE), a simple yet very effective algorithm to learn binary representation in an end-to-end fashion. By appending an ingeniously designed DBE layer to the deep convolutional neural network (DCNN), DBE learns binary code directly from the continuous DBE layer activation without quantization error. By employing the deep residual network (ResNet) as DCNN component, DBE captures rich semantics from images. Furthermore, in the effort of handling multilabel images, we design a joint cross entropy loss that includes both softmax cross entropy and weighted binary cross entropy in consideration of the correlation and independence of labels, respectively. Extensive experiments demonstrate the significant superiority of DBE over state-of-the-art methods on tasks of natural object recognition, image retrieval and image annotation.

📄 PDF Abstract BibTeX arXiv:1703.04960

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalObject RecognitionQuantizationRepresentation LearningRetrieval

Methods 이 논문이 사용한 방법론

DCNN Diffusion-convolutional neural networks (DCNN) is a model for graph-structured data. Through the introduction of a diffusion-convolution operation, diffusion-based representations…

Similar Papers 제목 키워드 기반

On the representation and embedding of knowledge bases beyond binary relations

2016-04-28 · Jianfeng Wen, Jian-Xin Li, Yongyi Mao, Shini Chen 외

The models developed to date for knowledge base embedding are all based on the assumption that the relations contained in knowledge bases are binary. For the training and testing of these embedding models, multi-fold (or…

Search Efficient Binary Network Embedding

2019-01-14 · Daokun Zhang, Jie Yin, Xingquan Zhu, Chengqi Zhang

Traditional network embedding primarily focuses on learning a continuous vector representation for each node, preserving network structure and/or node content information, such that off-the-shelf machine learning algorit…

AttributeNetwork EmbeddingNode ClassificationNode Clustering

Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings

2025-07-22 · Soumen Sinha, Shahryar Rahnamayan, Azam Asilian Bidgoli arxiv

Efficient text embedding is crucial for large-scale natural language processing (NLP) applications, where storage and computational efficiency are key concerns. In this paper, we explore how using binary representations …

Computational Efficiency

SAFE: Self-Attentive Function Embeddings for Binary Similarity

2018-11-13 · Luca Massarelli, Giuseppe Antonio Di Luna, Fabio Petroni, Leonardo Querzoni 외

The binary similarity problem consists in determining if two functions are similar by only considering their compiled form. Advanced techniques for binary similarity recently gained momentum as they can be applied in sev…

Malware AnalysisVulnerability Detection

On the Role of Pre-trained Embeddings in Binary Code Analysis

2025-02-12 · Alwin Maier, Felix Weissberg, Konrad Rieck

Deep learning has enabled remarkable progress in binary code analysis. In particular, pre-trained embeddings of assembly code have become a gold standard for solving analysis tasks, such as measuring code similarity or r…