# CoViT: Instance-Correspondence Contrastive Learning for Vision Transformer

arXiv: https://arxiv.org/abs/2609.01787 · HTML: https://mlsanity.com/paper/2609.01787/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment](https://mlsanity.com/paper/2207.13085/) (2022)
- [Toward Transformer-Based Object Detection](https://mlsanity.com/paper/2012.09958/) (2020)
- [White-Box Transformers via Sparse Rate Reduction](https://mlsanity.com/paper/2306.01129/) (2023)
- [ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection](https://mlsanity.com/paper/2304.08114/) (2023)
- [Learning CNN on ViT: A Hybrid Model to Explicitly Class-specific Boundaries for Domain Adaptation](https://mlsanity.com/paper/2403.18360/) (2024)
- [The Overlooked Classifier in Human-Object Interaction Recognition](https://mlsanity.com/paper/2112.06392/) (2021)
- [ViR:the Vision Reservoir](https://mlsanity.com/paper/2112.13545/) (2021)

## Abstract (arXiv)

Vision Transformers (ViT) excel in semantic understanding but fail to discriminate between object instances (e.g., identical embeddings for two dogs), limiting their use in instance-level tasks such as object detection and instance segmentation. We propose Contrastive Vision Transformer (CoViT), a self-supervised learning framework that injects instance-awareness into ViT through geometry-guided contrastive learning. CoViT uniquely coordinates ViT's attention maps and embeddings by constructing triplets: (1) Attention-guided masking: Refine multi-head attention via adaptive thresholding and morphological operations to generate instance masks, identifying foreground anchors; (2) Hardest contrastive mining: For each anchor, computing pairwise embedding similarities to select the intra-instance hardest positive (least similar patch within its mask) and inter-instance hardest negative (most similar patch from other instances), with intra-instance regions masked during negative search. These triplets drive a contrastive loss that simultaneously compresses intra-instance variance and expands inter-instance margins, forcing ViT to discern subtle geometric and appearance differences between instances. CoViT consistently achieves stable performance gains of over 2 AP points across multiple instance-level perception tasks by using ViT as backbone architecture. Notably, CoViT requires no extra decoders or labels, demonstrating that a pure ViT can learn instance-aware representations via inherent attention priors and targeted contrastive constraints. Code and models will be released.