Unity is Strength: Unifying Convolutional and Transformeral Features for Better Person Re-Identification

TL;DR

This paper introduces FusionReID, a novel framework that unifies CNNs and Transformers through mutual feature fusion to improve person re-identification accuracy across multiple benchmarks.

Contribution

The paper proposes a new fusion framework combining CNNs and Transformers with dual-attention mutual fusion for enhanced person ReID performance.

Findings

Achieves superior results on three public ReID benchmarks.

Effectively combines local and global features for better discrimination.

Demonstrates the effectiveness of dual-attention mutual fusion in ReID tasks.

Abstract

Person Re-identification (ReID) aims to retrieve the specific person across non-overlapping cameras, which greatly helps intelligent transportation systems. As we all know, Convolutional Neural Networks (CNNs) and Transformers have the unique strengths to extract local and global features, respectively. Considering this fact, we focus on the mutual fusion between them to learn more comprehensive representations for persons. In particular, we utilize the complementary integration of deep features from different model structures. We propose a novel fusion framework called FusionReID to unify the strengths of CNNs and Transformers for image-based person ReID. More specifically, we first deploy a Dual-branch Feature Extraction (DFE) to extract features through CNNs and Transformers from a single image. Moreover, we design a novel Dual-attention Mutual Fusion (DMF) to achieve sufficient feature fusions. The DMF comprises Local Refinement Units (LRU) and Heterogenous Transmission Modules (HTM). LRU utilizes depth-separable convolutions to align deep features in channel dimensions and spatial sizes. HTM consists of a Shared Encoding Unit (SEU) and two Mutual Fusion Units (MFU). Through the continuous stacking of HTM, deep features after LRU are repeatedly utilized to generate more discriminative features. Extensive experiments on three public ReID benchmarks demonstrate that our method can attain superior performances than most state-of-the-arts. The source code is available at https://github.com/924973292/FusionReID.