相关论文: Escaping The Big Data Paradigm in Self-Supervised …

Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…

Developing computational pathology models is essential for reducing manual tissue typing from whole slide images, transferring knowledge from the source domain to an unlabeled, shifted target domain, and identifying unseen categories. We…

In the field of medical images, although various works find Swin Transformer has promising effectiveness on pixelwise dense prediction, whether pre-training these models without using extra dataset can further boost the performance for the…

While Vision Transformers (ViT) have demonstrated remarkable performance across diverse tasks, their computational demands are substantial, scaling quadratically with the number of processed tokens. Compact attention representations,…

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it into individual object-level parts that can be matched and compared across different…

Nowadays, distributed smart cameras are deployed for a wide set of tasks in several application scenarios, ranging from object recognition, image retrieval, and forensic applications. Due to limited bandwidth in distributed systems,…

Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, question answering, etc. Although existing multimodal models present impressive…

Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based…

Vision Transformers (ViTs) have revolutionized computer vision, yet their self-attention mechanism lacks explicit spatial inductive biases, leading to suboptimal performance on spatially-structured tasks. Existing approaches introduce…

While visual imitation learning offers one of the most effective ways of learning from visual demonstrations, generalizing from them requires either hundreds of diverse demonstrations, task specific priors, or large, hard-to-train…

Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning. A seminal work, BEiT, casts MIM as a classification task with a visual vocabulary, tokenizing the…

Deep supervision, which involves extra supervisions to the intermediate features of a neural network, was widely used in image classification in the early deep learning era since it significantly reduces the training difficulty and eases…

We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed method takes token representations from the self-supervised ViT…

Humans develop visual intelligence through perceiving and interacting with their environment - a self-supervised learning process grounded in egocentric experience. Inspired by this, we ask how can artificial systems learn stable object…

Representation learning from Gigapixel Whole Slide Images (WSI) poses a significant challenge in computational pathology due to the complicated nature of tissue structures and the scarcity of labeled data. Multi-instance learning methods…

Deep Neural Networks are powerful tools for understanding complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. Saliency-Guided Training (SGT) methods try to…

Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing methods adopt a convolutional adapter to generate multi-scale…

BERT (Bidirectional Encoder Representations from Transformers) and related pre-trained Transformers have provided large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA). BERT is pre-trained on two…

Representation learning approaches typically rely on images of objects captured from a single perspective that are transformed using affine transformations. Additionally, self-supervised learning, a successful paradigm of representation…