REVIEW 6 cited by
A Survey on Visual Transformer
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism. Thanks to its strong representation capabilities, researchers are looking at ways to apply transformer to computer vision tasks. In a variety of visual benchmarks, transformer-based models perform similar to or better than other types of networks such as convolutional and recurrent neural networks. Given its high performance and less need for vision-specific inductive bias, transformer is receiving more and more attention from the computer vision community. In this paper, we review these vision transformer models by categorizing them in different tasks and analyzing their advantages and disadvantages. The main categories we explore include the backbone network, high/mid-level vision, low-level vision, and video processing. We also include efficient transformer methods for pushing transformer into real device-based applications. Furthermore, we also take a brief look at the self-attention mechanism in computer vision, as it is the base component in transformer. Toward the end of this paper, we discuss the challenges and provide several further research directions for vision transformers.
Forward citations
Cited by 6 Pith papers
-
Dynamic Structural Recovery Parameters Enhance Prediction of Visual Outcomes After Macular Hole Surgery
Dynamic recovery-rate features and a cross-attention multimodal network improve classification of postoperative BCVA improvement in macular hole patients, but the gain is partly from same-timepoint structural status r...
-
BRIGHT-VO: Brightness-Guided Hybrid Transformer for Visual Odometry with Multi-modality Refinement Module
A brightness-guided Transformer with IMU-based pose graph optimization improves monocular VO accuracy on synthetic low-light and KITTI benchmarks, though the evaluation has significant flaws.
-
FCL-ViT: Task-Aware Attention Tuning for Continual Learning
A frozen vision transformer plus trainable attention-steering blocks and EWC achieves competitive continual learning accuracy without rehearsal memory.
-
Self-Supervised Learning for Solar Radio Spectrum Classification
A masked autoencoder pretrained on ImageNet and fine-tuned on solar radio spectra reaches 99.5% classification accuracy, marginally outperforming supervised transfer learning baselines.
-
Enhancing Healthcare Recommendation Systems with a Multimodal LLMs-based MOE Architecture
A hybrid MOE-plus-LLM model is claimed to improve healthcare food recommendations, but the evidence is a small private dataset with no released code or error bars.
-
Recent Deep Learning in Crowd Behaviour Analysis: A Brief Review
A brief review of deep learning approaches for crowd behaviour prediction and recognition, with qualitative and quantitative comparisons, concluding that physics-inspired models perform best.
Discussion (0). Continue with ORCID to comment.