相关论文: SciLT: Long-tailed Image Classification under Scie…

Long-tailed learning has garnered increasing attention due to its practical significance. Among the various approaches, the fine-tuning paradigm has gained considerable interest with the advent of foundation models. However, most existing…

Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and multimodal dialogue. These improvements are evident in a wide…

Long-tailed visual recognition has received increasing attention in recent years. Due to the extremely imbalanced data distribution in long-tailed learning, the learning process shows great uncertainties. For example, the predictions of…

Supplementary Training on Intermediate Labeled-data Tasks (STILTs) is a widely applied technique, which first fine-tunes the pretrained language models on an intermediate task before on the target task of interest. While STILTs is able to…

Recently, data-driven deep saliency models have achieved high performance and have outperformed classical saliency models, as demonstrated by results on datasets such as the MIT300 and SALICON. Yet, there remains a large gap between the…

In real-world scenarios, human actions often fall into a long-tailed distribution. It makes the existing skeleton-based action recognition works, which are mostly designed based on balanced datasets, suffer from a sharp performance…

Although supervised finetuning (SFT) has emerged as an essential technique to align large language models with humans, it is considered superficial, with style learning being its nature. At the same time, recent works indicate the…

The upsurge in pre-trained large models started by ChatGPT has swept across the entire deep learning community. Such powerful models demonstrate advanced generative ability and multimodal understanding capability, which quickly set new…

A thorough and holistic scene understanding is crucial for autonomous vehicles, where LiDAR semantic segmentation plays an indispensable role. However, most existing methods focus on the network design while neglecting the inherent…

Balancing performance trade-off on long-tail (LT) data distributions remains a long-standing challenge. In this paper, we posit that this dilemma stems from a phenomenon called "tail performance degradation" (the model tends to severely…

In this paper, we present a semi-supervised fine-tuning approach designed to improve the performance of pre-trained foundation models on downstream tasks with limited labeled data. By leveraging content-style decomposition within an…

Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes. Recent methods propose to rebalance classes but…

Self-supervised learning (SSL) is an approach to extract useful feature representations from unlabeled data, and enable fine-tuning on downstream tasks with limited labeled examples. Self-pretraining is a SSL approach that uses the curated…

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…

In this work, we present GazeLT, a human visual attention integration-disintegration approach for long-tailed disease classification. A radiologist's eye gaze has distinct patterns that capture both fine-grained and coarser level disease…

Natural language understanding (NLU) has made massive progress driven by large benchmarks, but benchmarks often leave a long tail of infrequent phenomena underrepresented. We reflect on the question: have transfer learning methods…

Real-world data often exhibits a long-tailed distribution, in which head classes occupy most of the data, while tail classes only have very few samples. Models trained on long-tailed datasets have poor adaptability to tail classes and the…

Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors, particularly on large-scale lidar data. Surprisingly, although semantic class labels naturally follow a long-tailed distribution,…

The datasets used for Deep Neural Network training (e.g., ImageNet, MSCOCO, etc.) are often manually balanced across categories (classes) to facilitate learning of all the categories. This curation process is often expensive and requires…

Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We present a strategy for improving the performance and…