Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning
원문 초록
The workflow of extracting features from images using convolutional neural networks (CNN) and generating captions with recurrent neural networks (RNN) has become a de-facto standard for image captioning task. However, since CNN features are originally designed for classification task, it is mostly concerned with the main conspicuous element of the image, and often fails to correctly convey information on local, secondary elements. We propose to incorporate coding with vector of locally aggregated descriptors (VLAD) on spatial pyramid for CNN features of sub-regions in order to generate image representations that better reflect the local information of the images. Our results show that our method of compact VLAD coding can match CNN features with as little as 3% of dimensionality and, when combined with spatial pyramid, it results in image captions that more accurately take local elements into account.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation
Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport
토론
이 논문과 연결된 포럼 글이 아직 없습니다.