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.
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.
For these reasons, we address the computer-assisted search for prior art by creating a training dataset for supervised machine learning called PatentMatch.
We introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision.
In this paper, we present a fast exemplar-based image colorization approach using color embeddings named Color2Embed.
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.
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.
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.
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.