A survey of techniques for optimizing transformer inference
Recent years have seen a phenomenal rise in the performance and applications of
transformer neural networks. The family of transformer networks, including Bidirectional …
transformer neural networks. The family of transformer networks, including Bidirectional …
Vision transformers for dense prediction: A survey
S Zuo, Y Xiao, X Chang, X Wang - Knowledge-Based Systems, 2022 - Elsevier
Transformers have demonstrated impressive expressiveness and transfer capability in
computer vision fields. Dense prediction is a fundamental problem in computer vision that is …
computer vision fields. Dense prediction is a fundamental problem in computer vision that is …
Segment anything is not always perfect: An investigation of sam on different real-world applications
Abstract Recently, Meta AI Research approaches a general, promptable segment anything
model (SAM) pre-trained on an unprecedentedly large segmentation dataset (SA-1B) …
model (SAM) pre-trained on an unprecedentedly large segmentation dataset (SA-1B) …
SegFormer: Simple and efficient design for semantic segmentation with transformers
We present SegFormer, a simple, efficient yet powerful semantic segmentation framework
which unifies Transformers with lightweight multilayer perceptron (MLP) decoders …
which unifies Transformers with lightweight multilayer perceptron (MLP) decoders …
Transformer in transformer
Transformer is a new kind of neural architecture which encodes the input data as powerful
features via the attention mechanism. Basically, the visual transformers first divide the input …
features via the attention mechanism. Basically, the visual transformers first divide the input …
Pyramid vision transformer: A versatile backbone for dense prediction without convolutions
Although convolutional neural networks (CNNs) have achieved great success in computer
vision, this work investigates a simpler, convolution-free backbone network useful for many …
vision, this work investigates a simpler, convolution-free backbone network useful for many …
Transreid: Transformer-based object re-identification
Extracting robust feature representation is one of the key challenges in object re-
identification (ReID). Although convolution neural network (CNN)-based methods have …
identification (ReID). Although convolution neural network (CNN)-based methods have …
Transfg: A transformer architecture for fine-grained recognition
Fine-grained visual classification (FGVC) which aims at recognizing objects from
subcategories is a very challenging task due to the inherently subtle inter-class differences …
subcategories is a very challenging task due to the inherently subtle inter-class differences …
Multi-compound transformer for accurate biomedical image segmentation
The recent vision transformer (ie for image classification) learns non-local attentive
interaction of different patch tokens. However, prior arts miss learning the cross-scale …
interaction of different patch tokens. However, prior arts miss learning the cross-scale …
Dex-NeRF: Using a neural radiance field to grasp transparent objects
The ability to grasp and manipulate transparent objects is a major challenge for robots.
Existing depth cameras have difficulty detecting, localizing, and inferring the geometry of …
Existing depth cameras have difficulty detecting, localizing, and inferring the geometry of …