Region-Aware CLS Token Augmentation for Fine-Grained Image Retrieval

arXiv:2610.10991 · cs.CV, cs.LG · Submitted 2026-10-07 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-10-07

Updated: 2026-10-07

Terminology

• Transformer — 21× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Embeddings — 9× in this paper · explained in 2 episodes
• Computer Vision and Pattern Recognition — 5× in this paper
• Benchmark — 4× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• Stanford Online Products — 3× in this paper
• Accuracy — 2× in this paper · explained in 1 episode
• Asymmetric and Memory-Efficient Similarity Estimation — 2× in this paper
• CVF International Conference on Computer Vision — 2× in this paper
• Data Augmentation — 2× in this paper · explained in 7 episodes
• University of Sao Paulo — 2× in this paper
• Aggregation — 1× in this paper · explained in 1 episode
• Anchor Loss — 1× in this paper · explained in 1 episode
• Attention Mechanism — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Domain Shift — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Mean Average Precision — 1× in this paper
• Pruning — 1× in this paper · explained in 4 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Multi-Token Enhancing for Vision Representation Learning
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• DINOv2: Learning Robust Visual Features without Supervision
• On the Theoretical Limitations of Embedding-Based Retrieval
• Large-Scale Image Retrieval with Attentive Deep Local Features
• Unifying Deep Local and Global Features for Image Search
• Emerging Properties in Self-Supervised Vision Transformers
• detrex: Benchmarking Detection Transformers
• DINOv3
• Microsoft COCO: Common Objects in Context
• MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings
• Boosting vision transformers for image retrieval
• Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformers
• A Study on Token Pruning for ColBERT
• SOAR: Improved Indexing for Approximate Nearest Neighbor Search
• DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
• TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
• ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis
• Classification is a Strong Baseline for Deep Metric Learning
• Attention-based Ensemble for Deep Metric Learning

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models