相关论文: TransMix: Attend to Mix for Vision Transformers

Interpolation-based Data Augmentation (DA) methods (Mixup) linearly interpolate the inputs and labels of two or more training examples. Mixup has more recently been adapted to the field of Natural Language Processing (NLP), mainly for…

Vision Transformers have shown great potential in computer vision tasks. Most recent works have focused on elaborating the spatial token mixer for performance gains. However, we observe that a well-designed general architecture can…

Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities. Due to noises in web-harvested text-image pairs, however, scaling up…

The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for…

Obtaining object response maps is one important step to achieve weakly-supervised semantic segmentation using image-level labels. However, existing methods rely on the classification task, which could result in a response map only attending…

Cutmix-based data augmentation, which uses a cut-and-paste strategy, has shown remarkable generalization capabilities in deep learning. However, existing methods primarily consider global semantics with image-level constraints, which…

Vision Transformers (ViTs) have shown strong empirical performance on high-dimensional medical imaging data, yet their behavior under survival objectives and the interpretability of their attention mechanisms remain poorly understood. Under…

In this work, we propose data augmentation methods for embeddings from pre-trained deep learning models that take a weighted combination of a pair of input embeddings, as inspired by Mixup, and combine such augmentation with extra label…

Mixup refers to interpolation-based data augmentation, originally motivated as a way to go beyond empirical risk minimization (ERM). Yet, its extensions focus on the definition of interpolation and the space where it takes place, while the…

We investigate the integration of attention maps from a pre-trained Vision Transformer into voxel representations to enhance bimanual robotic manipulation. Specifically, we extract attention maps from DINOv2, a self-supervised ViT model,…

The successful application of deep learning to many visual recognition tasks relies heavily on the availability of a large amount of labeled data which is usually expensive to obtain. The few-shot learning problem has attracted increasing…

Non-overlapping patch-wise convolution is the default image tokenizer for all state-of-the-art vision Transformer (ViT) models. Even though many ViT variants have been proposed to improve its efficiency and accuracy, little research on…

The original ImageNet benchmark enforces a single-label assumption, despite many images depicting multiple objects. This leads to label noise and limits the richness of the learning signal. Multi-label annotations more accurately reflect…

Mixup generates augmented samples by linearly interpolating inputs and labels with a controllable ratio. However, since it operates in the latent embedding level, the resulting samples are not human-interpretable. In contrast, LLM-based…

Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited devices. To address this, researchers have dedicated…

This paper introduces MixTex, an end-to-end LaTeX OCR model designed for low-bias multilingual recognition, along with its novel data collection method. In applying Transformer architectures to LaTeX text recognition, we identified specific…

Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two sub-tasks: mixup generation and classification. However, the recent dominant online training method confines mixup to supervised learning (SL), and the…

The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e.g.…

Data augmentation is widely used to enhance generalization in visual classification tasks. However, traditional methods struggle when source and target domains differ, as in domain adaptation, due to their inability to address domain gaps.…

Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast…