Related papers: Vision Transformers for Small Histological Dataset…
Dataset distillation or condensation aims to generate a smaller but representative subset from a large dataset, which allows a model to be trained more efficiently, meanwhile evaluating on the original testing data distribution to achieve…
As deep vision models grow increasingly complex to achieve higher performance, deployment efficiency has become a critical concern. Knowledge distillation (KD) mitigates this issue by transferring knowledge from large teacher models to…
Striking a balance between precision and efficiency presents a prominent challenge in the bird's-eye-view (BEV) 3D object detection. Although previous camera-based BEV methods achieved remarkable performance by incorporating long-term…
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…
In recent years, Transformer-based architectures have become the dominant method for Computer Vision applications. While Transformers are explainable and scale well with dataset size, they lack the inductive biases of Convolutional Neural…
Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…
State-of-the-art vision pretraining methods rely on image-level self-distillation from object-centric datasets such as ImageNet, implicitly assuming each image contains a single object. This assumption does not always hold: many ImageNet…
Transformer-based detectors (DETRs) are becoming popular for their simple framework, but the large model size and heavy time consumption hinder their deployment in the real world. While knowledge distillation (KD) can be an appealing…
Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly…
Integrating deep learning applications into agricultural IoT systems faces a serious challenge of balancing the high accuracy of Vision Transformers (ViTs) with the efficiency demands of resource-constrained edge devices. Large transformer…
Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation and depth prediction. However, a fundamental capability…
Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…
Tissue phenotyping is a fundamental task in learning objective characterizations of histopathologic biomarkers within the tumor-immune microenvironment in cancer pathology. However, whole-slide imaging (WSI) is a complex computer vision in…
Automatic pavement distress classification facilitates improving the efficiency of pavement maintenance and reducing the cost of labor and resources. A recently influential branch of this task divides the pavement image into patches and…
In class incremental learning (CIL) setting, groups of classes are introduced to a model in each learning phase. The goal is to learn a unified model performant on all the classes observed so far. Given the recent popularity of Vision…
Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite their success, ViTs lack inductive biases, which can make it difficult to train them with limited data. To address this challenge, prior studies suggest training…
Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model…
Knowledge distillation is an effective paradigm for boosting the performance of pocket-size model, especially when multiple teacher models are available, the student would break the upper limit again. However, it is not economical to train…
Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more…
This paper discusses four facets of the Knowledge Distillation (KD) process for Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures, particularly when executed on edge devices with constrained processing…