Multi-Image Semantic Matching by Mining Consistent Features
This work proposes a multi-image matching method to estimate semantic correspondences across multiple images. In contrast to the previous methods that optimize all pairwise correspondences, the proposed method identifies and matches only a sparse set of reliable features in the image collection. In this way, the proposed method is able to prune nonrepeatable features and also highly scalable to handle thousands of images. We additionally propose a low-rank constraint to ensure the geometric consistency of feature correspondences over the whole image collection. Besides the competitive performance on multi-graph matching and semantic flow benchmarks, we also demonstrate the applicability of the proposed method for reconstructing object-class models and discovering object-class landmarks from images without using any annotation.
Code (2)
Tasks
Graph MatchingObjectSimilar Papers 제목 키워드 기반
Active Mining Sample Pair Semantics for Image-text Matching
Recently, commonsense learning has been a hot topic in image-text matching. Although it can describe more graphic correlations, commonsense learning still has some shortcomings: 1) The existing methods are based on tripl…
Active LearningImage-text matchingSemantic SimilaritySemantic Textual Similarity+2Object-Level Targeted Selection via Deep Template Matching
Retrieving images with objects that are semantically similar to objects of interest (OOI) in a query image has many practical use cases. A few examples include fixing failures like false negatives/positives of a learned …
Autonomous DrivingImage RetrievalObjectRetrieval+1Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networks
Text-to-image synthesis aims to generate a photo-realistic and semantic consistent image from a specific text description. The images synthesized by off-the-shelf models usually contain limited components compared with t…
Image GenerationContent-Consistent Matching for Domain Adaptive Semantic Segmentation
This paper considers the adaptation of semantic segmentation from the synthetic source domain to the real target domain. Different from most previous explorations that often aim at developing adversarial-based domain ali…
Domain AdaptationImage-to-Image TranslationSemantic SegmentationSynthetic-to-Real TranslationLanguage-agnostic Semantic Consistent Text-to-Image Generation
Recent GAN-based text-to-image generation models have advanced that they can generate photo-realistic images matching semantically with descriptions. However, research on multi-lingual text-to-image generation has not be…
Generative Adversarial NetworkImage GenerationMulti-lingual Text-to-Image GenerationMultilingual Text-to-Image Generation+2