Related papers: Learning Imbalanced Data with Vision Transformers

Deep neural networks frequently suffer from performance degradation when the training data is long-tailed because several majority classes dominate the training, resulting in a biased model. Recent studies have made a great effort in…

Real-world data often exhibit long-tailed distributions with numerous noisy labels, substantially degrading the performance of deep models. While prior research has made progress in addressing this combined challenge, it overlooks the…

The long-tailed class distribution in visual recognition tasks poses great challenges for neural networks on how to handle the biased predictions between head and tail classes, i.e., the model tends to classify tail classes as head classes.…

The relations expressed in user queries are vital for cross-modal information retrieval. Relation-focused cross-modal retrieval aims to retrieve information that corresponds to these relations, enabling effective retrieval across different…

Current popular backbones in computer vision, such as Vision Transformers (ViT) and ResNets are trained to perceive the world from 2D images. However, to more effectively understand 3D structural priors in 2D backbones, we propose Mask3D to…

Transformers have demonstrated great power in the recent development of large foundational models. In particular, the Vision Transformer (ViT) has brought revolutionary changes to the field of vision, achieving significant accomplishments…

Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…

This paper investigates the effectiveness of self-supervised pre-trained vision transformers (ViTs) compared to supervised pre-trained ViTs and conventional neural networks (ConvNets) for detecting facial deepfake images and videos. It…

There have been attempts to create large-scale structures in vision models similar to LLM, such as ViT-22B. While this research has provided numerous analyses and insights, our understanding of its practical utility remains incomplete.…

Fine-grained image recognition (FGIR) aims to distinguish visually similar sub-categories within a broader class, such as identifying bird species. While most existing FGIR methods rely on backbones pretrained on large-scale datasets like…

Although binary classification is a well-studied problem in computer vision, training reliable classifiers under severe class imbalance remains a challenging problem. Recent work has proposed techniques that mitigate the effects of training…

Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance. However, one significant drawback of ViTs is their…

Vision Transformers (ViTs) have emerged as the fundamental architecture for most computer vision fields, but the considerable memory and computation costs hinders their application on resource-limited devices. As one of the most powerful…

As most ''in the wild'' data collections of the natural world, the North America Camera Trap Images (NACTI) dataset shows severe long-tailed class imbalance, noting that the largest 'Head' class alone covers >50% of the 3.7M images in the…

In this work, we propose Visual-Predictive Instruction Tuning (VPiT) - a simple and effective extension to visual instruction tuning that enables a pretrained LLM to quickly morph into an unified autoregressive model capable of generating…

The learning of Transformation-Equivariant Representations (TERs), which is introduced by Hinton et al. \cite{hinton2011transforming}, has been considered as a principle to reveal visual structures under various transformations. It contains…

Implicit generative models are difficult to train as no explicit density functions are defined. Generative adversarial nets (GANs) present a minimax framework to train such models, which however can suffer from mode collapse due to the…

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…

Vision Transformer (ViT) and its variants (e.g., Swin, PVT) have achieved great success in various computer vision tasks, owing to their capability to learn long-range contextual information. Layer Normalization (LN) is an essential…

Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To…