Related papers: Gradient-Aware Logit Adjustment Loss for Long-tail…
Long-tail recognition tackles the natural non-uniformly distributed data in real-world scenarios. While modern classifiers perform well on populated classes, its performance degrades significantly on tail classes. Humans, however, are less…
Supervised Contrastive Loss (SCL) is popular in visual representation learning. Given an anchor image, SCL pulls two types of positive samples, i.e., its augmentation and other images from the same class together, while pushes negative…
In the real world, data tends to follow long-tailed distributions w.r.t. class or attribution, motivating the challenging Long-Tailed Recognition (LTR) problem. In this paper, we revisit recent LTR methods with promising Vision Transformers…
Gradient compression has surfaced as a key technique to address the challenge of communication efficiency in distributed learning. In distributed deep learning, however, it is observed that gradient distributions are heavy-tailed, with…
Long-tail learning has garnered widespread attention and achieved significant progress in recent times. However, even with pre-trained prior knowledge, models still exhibit weaker generalization performance on tail classes. The promising…
Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on…
The generalization gap on the long-tailed data sets is largely owing to most categories only occupying a few training samples. Decoupled training achieves better performance by training backbone and classifier separately. What causes the…
Object recognition in the real-world requires handling long-tailed or even open-ended data. An ideal visual system needs to recognize the populated head visual concepts reliably and meanwhile efficiently learn about emerging new tail…
The distribution of data in the world (eg, internet, etc.) significantly differs from the well-curated datasets and is often over-populated with samples from common categories. The algorithms designed for well-curated datasets perform…
Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training. However, long-tail knowledge from specialized domains is often scarce and underrepresented, rarely appearing in the models'…
Graph classification, aiming at learning the graph-level representations for effective class assignments, has received outstanding achievements, which heavily relies on high-quality datasets that have balanced class distribution. In fact,…
Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active…
Class imbalance remains a significant challenge in machine learning, particularly for tabular data classification tasks. While Gradient Boosting Decision Trees (GBDT) models have proven highly effective for such tasks, their performance can…
Real-world datasets commonly exhibit noisy labels and class imbalance, such as long-tailed distributions. While previous research addresses this issue by differentiating noisy and clean samples, reliance on information from predictions…
Many tasks in modern machine learning are observed to involve heavy-tailed gradient noise during the optimization process. To manage this realistic and challenging setting, new mechanisms, such as gradient clipping and gradient…
Convolutional neural networks have achieved great improvement on face recognition in recent years because of its extraordinary ability in learning discriminative features of people with different identities. To train such a well-designed…
We analyze neural scaling laws in a solvable model of last-layer fine-tuning where targets have intrinsic, instance-heterogeneous difficulty. In our Latent Instance Difficulty (LID) model, each input's target variance is governed by a…
We propose a distance supervised relation extraction approach for long-tailed, imbalanced data which is prevalent in real-world settings. Here, the challenge is to learn accurate "few-shot" models for classes existing at the tail of the…
Open-world long-tailed semi-supervised learning (OLSSL) has increasingly attracted attention. However, existing OLSSL algorithms generally assume that the distributions between known and novel categories are nearly identical. Against this…
Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes. While techniques have been proposed to achieve a more balanced training loss and to improve tail classes data…