mlsanityData to 14 Oct 2026

Embedding Compression for Efficient Re-Identification

arXiv 2405.14730 ↗First posted 23 May 2024cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Real world re-identfication (ReID) algorithms aim to map new observations of an object to previously recorded instances. These systems are often constrained by quantity and size of the stored embeddings. To combat this scaling problem, we attempt to shrink the size of these vectors by using a variety of compression techniques. In this paper, we benchmark quantization-aware-training along with three different dimension reduction methods: iterative structured pruning, slicing the embeddings at initialize, and using low rank embeddings. We find that ReID embeddings can be compressed by up to 96x with minimal drop in performance. This implies that modern re-identification paradigms do not fully leverage the high dimensional latent space, opening up further research to increase the capabilities of these systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 12 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

10 of 12 references.

References · 10

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  3. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  4. 2019The State of Sparsity in Deep Neural Networkscited by 476
  5. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 414
  6. 2016Person Re-identification in the Wildcited by 157
  7. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 96
  8. 2023To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Reviewcited by 72
  9. 2019Person Re-identification in Aerial Imagerycited by 36
  10. 2023UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identificationcited by 19

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification
  2. 2026RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search
  3. 2025Ultra-Efficient Decoding for End-to-End Neural Compression and Reconstruction
  4. 2022CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels
  5. 2026DiffReID: Discriminative Diffusion Model for Object Re-Identification
  6. 2023Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting
  7. 2024Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training
  8. 2026DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identification