Related papers: From Head to Tail: Towards Balanced Representation…

Deep learning-based models encounter challenges when processing long-tailed data in the real world. Existing solutions usually employ some balancing strategies or transfer learning to deal with the class imbalance problem, based on the…

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…

Data in the real world tends to exhibit a long-tailed label distribution, which poses great challenges for the training of neural networks in visual recognition. Existing methods tackle this problem mainly from the perspective of data…

The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, training these reasoning models, typically using Reinforcement…

Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below…

This paper examines the problems of severe image-text misalignment and high redundancy in the widely-used large-scale Vision-Language Pre-Training (VLP) datasets. To address these issues, we propose an efficient and straightforward…

3D perception plays an essential role for improving the safety and performance of autonomous driving. Yet, existing models trained on real-world datasets, which naturally exhibit long-tail distributions, tend to underperform on rare and…

Recently computer-aided diagnosis has demonstrated promising performance, effectively alleviating the workload of clinicians. However, the inherent sample imbalance among different diseases leads algorithms biased to the majority…

Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems which require extensive multi-step reasoning. This is primarily due to the progressive dilution…

Ensuring robust performance on long-tail examples is an important problem for many real-world applications of machine learning, such as autonomous driving. This work focuses on the problem of identifying rare examples within a corpus of…

Multi-modal Large Language Models (MLLMs) frequently face challenges from concept drift when dealing with real-world streaming data, wherein distributions change unpredictably. This mainly includes gradual drift due to long-tailed data and…

Large vision-language models (LVLMs) have shown premise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they require considerable computational resources for training and…

Several approaches have been proposed in recent literature to alleviate the long-tail problem, mainly in object classification tasks. In this paper, we make the first large-scale study concerning the task of Long-Tail Visual Relationship…

Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the…

The Large Vision-Language Model (LVLM) integrates computer vision and natural language processing techniques, offering substantial application potential. However, these models demand extensive resources during inference. Adaptive attention…

Real-world data usually present long-tailed distributions. Training on imbalanced data tends to render neural networks perform well on head classes while much worse on tail classes. The severe sparseness of training instances for the tail…

Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive capability in visual tasks, but their fine-tuning often suffers from bias in class-imbalanced scene. Recent works have introduced large language models…

The Large Vision-Language Model (LVLM) has enhanced the performance of various downstream tasks in visual-language understanding. Most existing approaches encode images and videos into separate feature spaces, which are then fed as inputs…

Real-world datasets often exhibit long-tailed distributions, where a few dominant "Head" classes have abundant samples while most "Tail" classes are severely underrepresented, leading to biased learning and poor generalization for the Tail.…