Semantic correspondence

44 papers with code • 4 benchmarks • 5 datasets

The task of semantic correspondence aims to establish reliable visual correspondence between different instances of the same object category.

Most implemented papers

Neighbourhood Consensus Networks

ignacio-rocco/ncnet NeurIPS 2018

Second, we demonstrate that the model can be trained effectively from weak supervision in the form of matching and non-matching image pairs without the need for costly manual annotation of point to point correspondences.

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

Shaoli-Huang/SnapMix 9 Dec 2020

As the main discriminative information of a fine-grained image usually resides in subtle regions, methods along this line are prone to heavy label noise in fine-grained recognition.

PatentMatch: A Dataset for Matching Patent Claims & Prior Art

julian-risch/PatentMatch 27 Dec 2020

For these reasons, we address the computer-assisted search for prior art by creating a training dataset for supervised machine learning called PatentMatch.

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision

NVlabs/DiscoBox ICCV 2021

We introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision.

Color2Embed: Fast Exemplar-Based Image Colorization using Color Embeddings

zhaohengyuan1/Color2Style 15 Jun 2021

In this paper, we present a fast exemplar-based image colorization approach using color embeddings named Color2Embed.

End-to-end weakly-supervised semantic alignment

ignacio-rocco/weakalign CVPR 2018

We tackle the task of semantic alignment where the goal is to compute dense semantic correspondence aligning two images depicting objects of the same category.

iSPA-Net: Iterative Semantic Pose Alignment Network

val-iisc/iSPA-Net 3 Aug 2018

Such image comparison based approach also alleviates the problem of data scarcity and hence enhances scalability of the proposed approach for novel object categories with minimal annotation.

Cost Aggregation Is All You Need for Few-Shot Segmentation

Seokju-Cho/Volumetric-Aggregation-Transformer 22 Dec 2021

We introduce a novel cost aggregation network, dubbed Volumetric Aggregation with Transformers (VAT), to tackle the few-shot segmentation task by using both convolutions and transformers to efficiently handle high dimensional correlation maps between query and support.

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

Seokju-Cho/Volumetric-Aggregation-Transformer 22 Jul 2022

However, the tokenization of a correlation map for transformer processing can be detrimental, because the discontinuity at token boundaries reduces the local context available near the token edges and decreases inductive bias.

Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks

matthewfl/nlp-entity-convnet NAACL 2016

A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts.