Deep long-tailed learning: A survey
Deep long-tailed learning, one of the most challenging problems in visual recognition, aims
to train well-performing deep models from a large number of images that follow a long-tailed …
to train well-performing deep models from a large number of images that follow a long-tailed …
Balanced contrastive learning for long-tailed visual recognition
Real-world data typically follow a long-tailed distribution, where a few majority categories
occupy most of the data while most minority categories contain a limited number of samples …
occupy most of the data while most minority categories contain a limited number of samples …
Parametric contrastive learning
In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed
recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to …
recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to …
Hierarchical dense correlation distillation for few-shot segmentation
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting
unseen classes with only a handful of annotations. Previous methods limited to the semantic …
unseen classes with only a handful of annotations. Previous methods limited to the semantic …
A survey on long-tailed visual recognition
L Yang, H Jiang, Q Song, J Guo - International Journal of Computer Vision, 2022 - Springer
The heavy reliance on data is one of the major reasons that currently limit the development
of deep learning. Data quality directly dominates the effect of deep learning models, and the …
of deep learning. Data quality directly dominates the effect of deep learning models, and the …
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
The booming of 3D recognition in the 2020s began with the introduction of point cloud
transformers. They quickly overwhelmed sparse CNNs and became state-of-the-art models …
transformers. They quickly overwhelmed sparse CNNs and became state-of-the-art models …
AnnoPRO: a strategy for protein function annotation based on multi-scale protein representation and a hybrid deep learning of dual-path encoding
Protein function annotation has been one of the longstanding issues in biological sciences,
and various computational methods have been developed. However, the existing methods …
and various computational methods have been developed. However, the existing methods …
Generalized parametric contrastive learning
In this paper, we propose the Generalized Parametric Contrastive Learning (GPaCo/PaCo)
which works well on both imbalanced and balanced data. Based on theoretical analysis, we …
which works well on both imbalanced and balanced data. Based on theoretical analysis, we …
Vl-ltr: Learning class-wise visual-linguistic representation for long-tailed visual recognition
Recently, computer vision foundation models such as CLIP and ALI-GN, have shown
impressive generalization capabilities on various downstream tasks. But their abilities to …
impressive generalization capabilities on various downstream tasks. But their abilities to …
Class-conditional sharpness-aware minimization for deep long-tailed recognition
It's widely acknowledged that deep learning models with flatter minima in its loss landscape
tend to generalize better. However, such property is under-explored in deep long-tailed …
tend to generalize better. However, such property is under-explored in deep long-tailed …