End-to-end object detection with transformers
We present a new method that views object detection as a direct set prediction problem. Our
approach streamlines the detection pipeline, effectively removing the need for many hand …
approach streamlines the detection pipeline, effectively removing the need for many hand …
Multi-label learning from single positive labels
Predicting all applicable labels for a given image is known as multi-label classification.
Compared to the standard multi-class case (where each image has only one label), it is …
Compared to the standard multi-class case (where each image has only one label), it is …
Orderless recurrent models for multi-label classification
VO Yazici, A Gonzalez-Garcia… - Proceedings of the …, 2020 - openaccess.thecvf.com
Recurrent neural networks (RNN) are popular for many computer vision tasks, including
multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered …
multi-label classification. Since RNNs produce sequential outputs, labels need to be ordered …
Generating unseen complex scenes: are we there yet?
A Casanova, M Drozdzal… - arXiv preprint arXiv …, 2020 - arxiv.org
Although recent complex scene conditional generation models generate increasingly
appealing scenes, it is very hard to assess which models perform better and why. This is …
appealing scenes, it is very hard to assess which models perform better and why. This is …
Simple and robust loss design for multi-label learning with missing labels
Multi-label learning in the presence of missing labels (MLML) is a challenging problem.
Existing methods mainly focus on the design of network structures or training schemes …
Existing methods mainly focus on the design of network structures or training schemes …
Plmcl: Partial-label momentum curriculum learning for multi-label image classification
Multi-label image classification aims to predict all possible labels in an image. It is usually
formulated as a partial-label learning problem, given the fact that it could be expensive in …
formulated as a partial-label learning problem, given the fact that it could be expensive in …
Learning to substitute ingredients in recipes
Recipe personalization through ingredient substitution has the potential to help people meet
their dietary needs and preferences, avoid potential allergens, and ease culinary exploration …
their dietary needs and preferences, avoid potential allergens, and ease culinary exploration …
G2netpl: Generic game-theoretic network for partial-label image classification
Multi-label image classification aims to predict all possible labels in an image. It is usually
formulated as a partial-label learning problem, since it could be expensive in practice to …
formulated as a partial-label learning problem, since it could be expensive in practice to …
Date: Dual assignment for end-to-end fully convolutional object detection
Fully convolutional detectors discard the one-to-many assignment and adopt a one-to-one
assigning strategy to achieve end-to-end detection but suffer from the slow convergence …
assigning strategy to achieve end-to-end detection but suffer from the slow convergence …
Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations
Object-centric methods have seen significant progress in unsupervised decomposition of
raw perception into rich object-like abstractions. However, limited ability to ground object …
raw perception into rich object-like abstractions. However, limited ability to ground object …