Related papers: Towards Flexible Inductive Bias via Progressive Re…

Achieving precise alignment between user intent and generated visuals remains a central challenge in text-to-visual generation, as a single attempt often fails to produce the desired output. To handle this, prior approaches mainly scale the…

Visual object recognition has been extensively studied in both neuroscience and computer vision. Recently, the most popular class of artificial systems for this task, deep convolutional neural networks (CNNs), has been shown to provide…

Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…

Neural networks are often trained on multiple tasks, either simultaneously (multi-task learning, MTL) or sequentially (pretraining and subsequent finetuning, PT+FT). In particular, it is common practice to pretrain neural networks on a…

Recent advances in Vision Transformer (ViT) have demonstrated its impressive performance in image classification, which makes it a promising alternative to Convolutional Neural Network (CNN). Unlike CNNs, ViT represents an input image as a…

An accurate velocity model is essential to make a good seismic image. Conventional methods to perform Velocity Model Building (VMB) tasks rely on inverse methods, which, despite being widely used, are ill-posed problems that require intense…

Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known as prompts, which steer the frozen pretrained ViTs. Although VPT has…

This paper presents PreVIous, a methodology to predict the performance of convolutional neural networks (CNNs) in terms of throughput and energy consumption on vision-enabled devices for the Internet of Things. CNNs typically constitute a…

Despite the widespread adoption of transformers in medical applications, the exploration of multi-scale learning through transformers remains limited, while hierarchical representations are considered advantageous for computer-aided medical…

Structured pruning compresses neural networks by reducing channels (filters) for fast inference and low footprint at run-time. To restore accuracy after pruning, fine-tuning is usually applied to pruned networks. However, too few remaining…

The quality and richness of feature maps extracted by convolution neural networks (CNNs) and vision Transformers (ViTs) directly relate to the robust model performance. In medical computer vision, these information-rich features are crucial…

We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by backpropagation - a computationally efficient procedure that…

Land Use Scene Classification (LUSC) from remote sensing imagery plays a critical role in environmental monitoring, urban planning, and sustainable resource management. In recent years, deep learning methods have significantly advanced the…

Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable prompt tokens into the token sequence at each layer. However, we observe that existing VPT variants often…

Vision Transformers (ViTs) have gained significant popularity in recent years and have proliferated into many applications. However, their behavior under different learning paradigms is not well explored. We compare ViTs trained through…

Learning-based precoding has been shown able to be implemented in real-time, jointly optimized with channel acquisition, and robust to imperfect channels. Yet previous works rarely explain the design choices and learning performance, and…

Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. However, ViT lacks the inductive bias inherent to convolution making it require a large amount of…

Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices. We explore the sparsity in ViT and observe that…

Despite the initial belief that Convolutional Neural Networks (CNNs) are driven by shapes to perform visual recognition tasks, recent evidence suggests that texture bias in CNNs provides higher performing models when learning on large…

Conventional wisdom suggests that pre-training Vision Transformers (ViT) improves downstream performance by learning useful representations. Is this actually true? We investigate this question and find that the features and representations…