# VisNet: Efficient Person Re-Identification via Alpha-Divergence Loss, Feature Fusion and Dynamic Multi-Task Learning

arXiv: https://arxiv.org/abs/2601.00307 · HTML: https://mlsanity.com/paper/2601.00307/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 1 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks](https://mlsanity.com/paper/2303.17602/) (2023)
- [A Discriminatively Learned CNN Embedding for Person Re-identification](https://mlsanity.com/paper/1611.05666/) (2016)
- [A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking](https://mlsanity.com/paper/1711.10378/) (2017)
- [Part-based Pseudo Label Refinement for Unsupervised Person Re-identification](https://mlsanity.com/paper/2203.14675/) (2022)
- [AANet: Attribute Attention Network for Person Re-Identifications](https://mlsanity.com/paper/1912.09021/) (2019)
- [SVDNet for Pedestrian Retrieval](https://mlsanity.com/paper/1703.05693/) (2017)
- [Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification](https://mlsanity.com/paper/2104.01546/) (2021)
- [Beyond Triplet Loss: Person Re-identification with Fine-grained Difference-aware Pairwise Loss](https://mlsanity.com/paper/2009.10295/) (2020)

## Abstract (arXiv)

Person re-identification (ReID) is an extremely important area in both surveillance and mobile applications, requiring strong accuracy with minimal computational cost. State-of-the-art methods give good accuracy but with high computational budgets. To remedy this, this paper proposes VisNet, a computationally efficient and effective re-identification model suitable for real-world scenarios. It is the culmination of conceptual contributions, including feature fusion at multiple scales with automatic attention on each, semantic clustering with anatomical body partitioning, a dynamic weight averaging technique to balance classification semantic regularization, and the use of loss function FIDI for improved metric learning tasks. The multiple scales fuse ResNet50's stages 1 through 4 without the use of parallel paths, with semantic clustering introducing spatial constraints through the use of rule-based pseudo-labeling. VisNet achieves 87.05% Rank-1 and 77.65% mAP on the Market-1501 dataset, having 32.41M parameters and 4.601 GFLOPs, hence, proposing a practical approach for real-time deployment in surveillance and mobile applications where computational resources are limited.