# HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping

arXiv: https://arxiv.org/abs/2312.17492 · HTML: https://mlsanity.com/paper/2312.17492/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 47 references that are in the map.
- First posted on arXiv 29 Dec 2023.

## Builds on (most cited first, 30 of 32)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [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)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [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)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals](https://mlsanity.com/paper/2102.06191/) (2021)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut](https://mlsanity.com/paper/2202.11539/) (2022)
- [Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization](https://mlsanity.com/paper/2205.07839/) (2022)
- [FreeSOLO: Learning to Segment Objects without Annotations](https://mlsanity.com/paper/2202.12181/) (2022)
- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [Self-Supervised Visual Representation Learning with Semantic Grouping](https://mlsanity.com/paper/2205.15288/) (2022)
- [Unsupervised Object Localization: Observing the Background to Discover Objects](https://mlsanity.com/paper/2212.07834/) (2022)
- [Toward unsupervised, multi-object discovery in large-scale image collections](https://mlsanity.com/paper/2007.02662/) (2020)
- [Unsupervised Salient Object Detection with Spectral Cluster Voting](https://mlsanity.com/paper/2203.12614/) (2022)
- [Large-Scale Unsupervised Object Discovery](https://mlsanity.com/paper/2106.06650/) (2021)
- [Unsupervised Image Matching and Object Discovery as Optimization](https://mlsanity.com/paper/1904.03148/) (2019)

## Built on by (most cited first, 10 of 10)

- [Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors](https://mlsanity.com/paper/2503.20211/) (2025)
- [RGB-to-Polarization Estimation: A New Task and Benchmark Study](https://mlsanity.com/paper/2505.13050/) (2025)
- [3DOT: Texture Transfer for 3DGS Objects from a Single Reference Image](https://mlsanity.com/paper/2503.18853/) (2025)
- [unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning](https://mlsanity.com/paper/2506.01778/) (2025)
- [ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation](https://mlsanity.com/paper/2509.00665/) (2025)
- [GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes](https://mlsanity.com/paper/2605.23602/) (2026)
- [Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO](https://mlsanity.com/paper/2607.11581/) (2026)
- [Object Concepts Emerge from Motion](https://mlsanity.com/paper/2505.21635/) (2025)
- [UC-VLM: Consistency-Driven Learning for AI-Generated Image Detection with Vision-Language Large Models](https://mlsanity.com/paper/2608.15238/) (2026)
- [Object Concepts Emerge from Motion](https://mlsanity.com/paper/2609.04348/) (2026)

## Abstract (arXiv)

Unsupervised object discovery and localization aims to detect or segment objects in an image without any supervision. Recent efforts have demonstrated a notable potential to identify salient foreground objects by utilizing self-supervised transformer features. However, their scopes only build upon patch-level features within an image, neglecting region/image-level and cross-image relationships at a broader scale. Moreover, these methods cannot differentiate various semantics from multiple instances. To address these problems, we introduce Hierarchical mErging framework via contrAstive grouPing (HEAP). Specifically, a novel lightweight head with cross-attention mechanism is designed to adaptively group intra-image patches into semantically coherent regions based on correlation among self-supervised features. Further, to ensure the distinguishability among various regions, we introduce a region-level contrastive clustering loss to pull closer similar regions across images. Also, an image-level contrastive loss is present to push foreground and background representations apart, with which foreground objects and background are accordingly discovered. HEAP facilitates efficient hierarchical image decomposition, which contributes to more accurate object discovery while also enabling differentiation among objects of various classes. Extensive experimental results on semantic segmentation retrieval, unsupervised object discovery, and saliency detection tasks demonstrate that HEAP achieves state-of-the-art performance.