相关论文: Inducing Spatial Locality in Vision Transformers t…

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…

Recent state-of-the-art performances of Vision Transformers (ViT) in computer vision tasks demonstrate that a general-purpose architecture, which implements long-range self-attention, could replace the local feature learning operations of…

Deep-Learning-based video recognition has shown promising improvements along with the development of large-scale datasets and spatiotemporal network architectures. In image recognition, learning spatially invariant features is a key factor…

A central objective in computer vision is to design models with appropriate 2-D inductive bias. Desiderata for 2D inductive bias include two-dimensional position awareness, dynamic spatial locality, and translation and permutation…

Visual Instruction Finetuning (VIF) is pivotal for post-training Vision-Language Models (VLMs). Unlike unimodal instruction finetuning in plain-text large language models, which mainly requires instruction datasets to enable model…

In fine-grained image recognition (FGIR), the localization and amplification of region attention is an important factor, which has been explored a lot by convolutional neural networks (CNNs) based approaches. The recently developed vision…

Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…

Recently, Deep Learning (DL) techniques have been used for User Equipment (UE) positioning. However, the key shortcomings of such models is that: i) they weigh the same attention to the entire input; ii) they are not well suited for the…

We propose an adaptation to the training of Vision Transformers (ViTs) that allows for an explicit modeling of objects during the attention computation. This is achieved by adding a new branch to selected attention layers that computes an…

Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformers in similar scenarios, particularly under label noise,…

The training of vision transformer (ViT) networks on small-scale datasets poses a significant challenge. By contrast, convolutional neural networks (CNNs) have an architectural inductive bias enabling them to perform well on such problems.…

Recently, Vision-Language foundation models like CLIP and ALIGN, which are pre-trained on large-scale data have shown remarkable zero-shot generalization to diverse datasets with different classes and even domains. In this work, we take a…

Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, these models are extremely memory intensive during their…

Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with input resolutions that are unseen during training. We…

The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of…

Visual Place Recognition (VPR) is a scene-oriented image retrieval problem in computer vision in which re-ranking based on local features is commonly employed to improve performance. In robotics, VPR is also referred to as Loop Closure…

Vision Transformers (ViTs) have demonstrated strong capabilities in interpreting complex medical imaging data. However, their significant computational and memory demands pose challenges for deployment in real-time, resource-constrained…

Integrating new class information without losing previously acquired knowledge remains a central challenge in artificial intelligence, often referred to as catastrophic forgetting. Few-shot class incremental learning (FSCIL) addresses this…

Deep learning models often rely only on a small set of features even when there is a rich set of predictive signals in the training data. This makes models brittle and sensitive to distribution shifts. In this work, we first examine vision…

Vision Transformers (ViTs) have demonstrated remarkable success on large-scale datasets, but their performance on smaller datasets often falls short of convolutional neural networks (CNNs). This paper explores the design and optimization of…