# There is no SAMantics! Exploring SAM as a Backbone for Visual Understanding Tasks

arXiv: https://arxiv.org/abs/2411.15288 · HTML: https://mlsanity.com/paper/2411.15288/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 62 references that are in the map.
- First posted on arXiv 22 Nov 2024.

## Builds on (most cited first, 30 of 55)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [Images Speak in Images: A Generalist Painter for In-Context Visual Learning](https://mlsanity.com/paper/2212.02499/) (2022)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)

## Built on by (most cited first, 7 of 7)

- [No time to train! Training-Free Reference-Based Instance Segmentation](https://mlsanity.com/paper/2507.02798/) (2025)
- [AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models](https://mlsanity.com/paper/2506.09082/) (2025)
- [SAM2-UNeXT: An Improved High-Resolution Baseline for Adapting Foundation Models to Downstream Segmentation Tasks](https://mlsanity.com/paper/2508.03566/) (2025)
- [Evaluating an Adaptive Multispectral Turret System for Autonomous Tracking Across Variable Illumination Conditions](https://mlsanity.com/paper/2512.22263/) (2025)
- [Learning Generalizable 3D Medical Image Representations from Mask-Guided Self-Supervision](https://mlsanity.com/paper/2603.13660/) (2026)
- [Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Tasks](https://mlsanity.com/paper/2605.16864/) (2026)
- [Text-to-seed generation: Training-free open-vocabulary seeded semantic segmentation via re-purposing diffusion as text-guided seed generator](https://mlsanity.com/paper/2608.26624/) (2026)

## Abstract (arXiv)

The Segment Anything Model (SAM) was originally designed for label-agnostic mask generation. Does this model also possess inherent semantic understanding, of value to broader visual tasks? In this work we follow a multi-staged approach towards exploring this question. We firstly quantify SAM's semantic capabilities by comparing base image encoder efficacy under classification tasks, in comparison with established models (CLIP and DINOv2). Our findings reveal a significant lack of semantic discriminability in SAM feature representations, limiting potential for tasks that require class differentiation. This initial result motivates our exploratory study that attempts to enable semantic information via in-context learning with lightweight fine-tuning where we observe that generalisability to unseen classes remains limited. Our observations culminate in the proposal of a training-free approach that leverages DINOv2 features, towards better endowing SAM with semantic understanding and achieving instance-level class differentiation through feature-based similarity. Our study suggests that incorporation of external semantic sources provides a promising direction for the enhancement of SAM's utility with respect to complex visual tasks that require semantic understanding.