Related papers: SeiT++: Masked Token Modeling Improves Storage-eff…

Token-based masked generative models are gaining popularity for their fast inference time with parallel decoding. While recent token-based approaches achieve competitive performance to diffusion-based models, their generation performance is…

Finetuning a pretrained backbone in the encoder part of an image transformer network has been the traditional approach for the semantic segmentation task. However, such an approach leaves out the semantic context that an image provides…

Deep learning has achieved remarkable success in modeling sequential data, including event sequences, temporal point processes, and irregular time series. Recently, transformers have largely replaced recurrent networks in these tasks.…

This paper focuses on Semi-Supervised Object Detection (SSOD). Knowledge Distillation (KD) has been widely used for semi-supervised image classification. However, adapting these methods for SSOD has the following obstacles. (1) The teacher…

Supervised fine-tuning methods (SFT) perform great efficiency on artificial intelligence interpretation in SAR images, leveraging the powerful representation knowledge from pre-training models. Due to the lack of domain-specific pre-trained…

The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations. However, such annotations are often tedious and expensive to collect. Semi-supervised learning is a good…

The rapid success of Vision Large Language Models (VLLMs) often depends on the high-resolution images with abundant visual tokens, which hinders training and deployment efficiency. Current training-free visual token compression methods…

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…

This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let…

We propose a Deep Texture Encoding Network (Deep-TEN) with a novel Encoding Layer integrated on top of convolutional layers, which ports the entire dictionary learning and encoding pipeline into a single model. Current methods build from…

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the…

We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image…

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…

Quality assessment and aesthetics assessment aim to evaluate the perceived quality and aesthetics of visual content. Current learning-based methods suffer greatly from the scarcity of labeled data and usually perform sub-optimally in terms…

Current self-supervised learning algorithms are often modality-specific and require large amounts of computational resources. To address these issues, we increase the training efficiency of data2vec, a learning objective that generalizes…

Active learning, a widely adopted technique for enhancing machine learning models in text and image classification tasks with limited annotation resources, has received relatively little attention in the domain of Named Entity Recognition…

Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing…

Training deep learning models, particularly Transformer-based architectures such as Large Language Models (LLMs), demands substantial computational resources and extended training periods. While optimal configuration and infrastructure…