Related papers: Bridging The Gaps Between Token Pruning and Full P…

Token compression techniques have recently emerged as powerful tools for accelerating Vision Transformer (ViT) inference in computer vision. Due to the quadratic computational complexity with respect to the token sequence length, these…

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…

When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain. If the target domain covers a smaller visual…

Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder…

Vision Transformers (ViTs) have achieved state-of-the-art performance across various computer vision tasks, but their high computational cost remains a challenge. Token pruning has been proposed to reduce this cost by selectively removing…

Since its inception, Vision Transformer (ViT) has emerged as a prevalent model in the computer vision domain. Nonetheless, the multi-head self-attention (MHSA) mechanism in ViT is computationally expensive due to its calculation of…

While transformers have surpassed convolutional neural networks (CNNs) in various computer vision tasks, microelectronics defect detection still largely relies on CNNs. We hypothesize that this gap is due to the fact that a) transformers…

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs…

Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue. Since the computation complexity of ViT is quadratic with respect to the input sequence length, a mainstream…

Recently, vision transformer (ViT) and its variants have achieved promising performances in various computer vision tasks. Yet the high computational costs and training data requirements of ViTs limit their application in…

In the present work we present Training Noise Token (TNT) Pruning for vision transformers. Our method relaxes the discrete token dropping condition to continuous additive noise, providing smooth optimization in training, while retaining…

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed…

The ability to predict future visual observations conditioned on past observations and motor commands can enable embodied agents to plan solutions to a variety of tasks in complex environments. This work shows that we can create good video…

While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling…

Masked Autoencoders (MAE) achieve self-supervised learning of image representations by randomly removing a portion of visual tokens and reconstructing the original image as a pretext task, thereby significantly enhancing pretraining…

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…

Cutting-edge research in facial expression recognition (FER) currently favors the utilization of convolutional neural networks (CNNs) backbone which is supervisedly pre-trained on face recognition datasets for feature extraction. However,…

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…