Litcius/Paper detail

Dynamic Unary Convolution in Transformers

Haoran Duan, Yang Long, Shidong Wang, Haofeng Zhang, Chris G. Willcocks, Ling Shao

2023IEEE Transactions on Pattern Analysis and Machine Intelligence42 citationsDOIOpen Access PDF

Abstract

It is uncertain whether the power of transformer architectures can complement existing convolutional neural networks. A few recent attempts have combined convolution with transformer design through a range of structures in series, where the main contribution of this paper is to explore a parallel design approach. While previous transformed-based approaches need to segment the image into patch-wise tokens, we observe that the multi-head self-attention conducted on convolutional features is mainly sensitive to global correlations and that the performance degrades when these correlations are not exhibited. We propose two parallel modules along with multi-head self-attention to enhance the transformer. For local information, a dynamic local enhancement module leverages convolution to dynamically and explicitly enhance positive local patches and suppress the response to less informative ones. For mid-level structure, a novel unary co-occurrence excitation module utilizes convolution to actively search the local co-occurrence between patches. The parallel-designed Dynamic Unary Convolution in Transformer (DUCT) blocks are aggregated into a deep architecture, which is comprehensively evaluated across essential computer vision tasks in image-based classification, segmentation, retrieval and density estimation. Both qualitative and quantitative results show our parallel convolutional-transformer approach with dynamic and unary convolution outperforms existing series-designed structures.

Topics & Concepts

Computer scienceUnary operationConvolutional neural networkSegmentationTransformerArtificial intelligenceInferenceConvolution (computer science)Pattern recognition (psychology)RectangleImage segmentationAlgorithmComputer visionArtificial neural networkMathematicsEngineeringVoltageGeometryElectrical engineeringCombinatoricsAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningAnomaly Detection Techniques and Applications
Dynamic Unary Convolution in Transformers | Litcius