Related papers: Equalized Focal Loss for Dense Long-Tailed Object …
In the real world, the frequency of occurrence of objects is naturally skewed forming long-tail class distributions, which results in poor performance on the statistically rare classes. A promising solution is to mine tail-class examples to…
Federated learning involves training machine learning models over devices or data silos, such as edge processors or data warehouses, while keeping the data local. Training in heterogeneous and potentially massive networks introduces bias…
Recent advancements have illuminated the efficacy of some tensorization-decomposition Parameter-Efficient Fine-Tuning methods like LoRA and FacT in the context of Vision Transformers (ViT). However, these methods grapple with the challenges…
Data is the foundation for the development of computer vision, and the establishment of datasets plays an important role in advancing the techniques of fine-grained visual categorization~(FGVC). In the existing FGVC datasets used in…
In vision domain, large-scale natural datasets typically exhibit long-tailed distribution which has large class imbalance between head and tail classes. This distribution poses difficulty in learning good representations for tail classes.…
Edge detection, a basic task in the field of computer vision, is an important preprocessing operation for the recognition and understanding of a visual scene. In conventional models, the edge image generated is ambiguous, and the edge lines…
Fine-grained visual classification is a challenging task that recognizes the sub-classes belonging to the same meta-class. Large inter-class similarity and intra-class variance is the main challenge of this task. Most exiting methods try to…
Temporal action segmentation in untrimmed procedural videos aims to densely label frames into action classes. These videos inherently exhibit long-tailed distributions, where actions vary widely in frequency and duration. In temporal action…
The visual world naturally exhibits an imbalance in the number of object or scene instances resulting in a \emph{long-tailed distribution}. This imbalance poses significant challenges for classification models based on deep learning.…
Federated Learning (FL) is plagued by two key challenges: high communication overhead and performance collapse on heterogeneous (non-IID) data. Analytic FL (AFL) provides a single-round, data distribution invariant solution, but is limited…
While long-tailed semi-supervised learning (LTSSL) has attracted growing attention in many real-world classification tasks, existing LTSSL algorithms typically assume that labeled and unlabeled data share nearly identical class…
Multi-task learning (MTL) aims to build general-purpose vision systems by training a single network to perform multiple tasks jointly. While promising, its potential is often hindered by "unbalanced optimization", where task interference…
In the long-tailed recognition field, the Decoupled Training paradigm has demonstrated remarkable capabilities among various methods. This paradigm decouples the training process into separate representation learning and classifier…
Real-world data universally confronts a severe class-imbalance problem and exhibits a long-tailed distribution, i.e., most labels are associated with limited instances. The na\"ive models supervised by such datasets would prefer dominant…
Continual Learning enables models to learn and adapt to new tasks while retaining prior knowledge. Introducing new tasks, however, can naturally lead to feature entanglement across tasks, limiting the model's capability to distinguish…
Long-tailed distributions in class-imbalanced data present a fundamental challenge for deep learning models, which tend to be biased toward majority classes. While recent methods for long-tailed recognition have mitigated this issue, they…
Long-tailed multi-label visual recognition (LTML) task is a highly challenging task due to the label co-occurrence and imbalanced data distribution. In this work, we propose a unified framework for LTML, namely prompt tuning with…
Conventional multi-label classification (MLC) methods assume that all samples are fully labeled and identically distributed. Unfortunately, this assumption is unrealistic in large-scale MLC data that has long-tailed (LT) distribution and…
This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature. We propose a novel pseudo-labeling-based detector called…
A significant challenge in achieving ubiquitous Artificial Intelligence is the limited ability of models to rapidly learn new information in real-world scenarios where data follows long-tailed distributions, all while avoiding forgetting…