End-to-end object detection with transformers

N Carion, F Massa, G Synnaeve, N Usunier… - European conference on …, 2020 - Springer
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 …

Multi-label learning from single positive labels

E Cole, O Mac Aodha, T Lorieul… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …

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 …

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 …

Simple and robust loss design for multi-label learning with missing labels

Y Zhang, Y Cheng, X Huang, F Wen, R Feng… - arXiv preprint arXiv …, 2021 - arxiv.org
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 …

Plmcl: Partial-label momentum curriculum learning for multi-label image classification

R Abdelfattah, X Zhang, Z Wu, X Wu, X Wang… - … on Computer Vision, 2022 - Springer
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 …

Learning to substitute ingredients in recipes

B Fatemi, Q Duval, R Girdhar, M Drozdzal… - arXiv preprint arXiv …, 2023 - arxiv.org
Recipe personalization through ingredient substitution has the potential to help people meet
their dietary needs and preferences, avoid potential allergens, and ease culinary exploration …

G2netpl: Generic game-theoretic network for partial-label image classification

R Abdelfattah, X Zhang, MM Fouda, X Wang… - arXiv preprint arXiv …, 2022 - arxiv.org
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 …

Date: Dual assignment for end-to-end fully convolutional object detection

Y Chen, Q Chen, Q Hu, J Cheng - arXiv preprint arXiv:2211.13859, 2022 - arxiv.org
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 …

Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations

B Dedhia, NK Jha - arXiv preprint arXiv:2403.07887, 2024 - arxiv.org
Object-centric methods have seen significant progress in unsupervised decomposition of
raw perception into rich object-like abstractions. However, limited ability to ground object …