arXiv Computer Vision September 4, 2026 By Young Seok Jeon, Beatrice Brown-Mulry, Rohan Satya Isaac, Anjana Dissanayaka, Theo Dapamede, Mohammadreza Chavoshi, Judy Gichoya, Hari Trivedi

Solving the Needle-in-a-Haystack Problem in Mammography Vision-Language Model with Differentiable Subset Sampling

Read the original on arXiv Computer Vision →

The paper introduces TopKSigLIP, a vision‑language model tailored for mammography that tackles two key challenges: high‑resolution imaging and homogeneous radiology reports. It replaces standard CLIP training with a TopK‑Patch module that selects sparse high‑resolution patches likely to contain lesions, and a Sup‑sigmoid loss that uses soft labels from structured data instead of contrastive loss. TopKSigLIP outperforms existing open‑source mammography and general medical VLMs on zero‑shot tasks such as density assessment, BI‑RADS classification, finding subtyping, and cancer prediction, while also providing better lesion localization than Grad‑CAM.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv Computer Vision

Oct 9

Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification

The paper introduces a counterfactual data augmentation method that generates healthy mammograms by inpainting lesions with realistic normal tissue using a Denoising Diffusion Probabilistic Model and a RePaint-based sampling strategy. The generated healthy counterfactuals preserve patient-specific anatomy and match the quality of the original dataset, as confirmed by similarity metrics and radiologist assessment. When applied to four different classifier architectures on the VinDr-Mammo dataset, the augmentation improves sensitivity, especially at 80% fixed specificity, thereby enhancing the reliability of computer-aided breast cancer screening systems.

By In\^es Cruchinho Garcia, Mariana Mour\~ao, Francisco Maria Calisto, Carlos Santiago, Jacinto Nascimento

llms diffusion computer-vision multimodal

arXiv AI

Sep 1

ActiveAugment: Online Active Learning for Augmentation Selection in Deep Learning

arXiv:2608.28923v1 Announce Type: cross Abstract: Data augmentation is a cornerstone of deep learning pipelines, yet existing strategies treat it as a static, model-agnostic preprocessing step, eithe...

By Noah Videcrantz, Mostafa Mehdipour Ghazi

llms fine-tuning benchmarks

arXiv AI

Jul 14

Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift

arXiv:2607. 10358v1 Announce Type: cross Abstract: Foundation models are increasingly used as image feature extractors for mammography, but their robustness under external domain shift remains unclear.

By Giang Nguyen, Raghav Mehta, Emma A. M. Stanley, Tian Xia, Thi Hao Nguyen, Hieu Pham, Ben Glocker

llms multimodal benchmarks

arXiv Machine Learning

Jun 3

GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations

arXiv:2606. 03180v1 Announce Type: cross Abstract: Vision-language models (VLMs) for radiology have emerged as a scalable paradigm by leveraging image-report pairs naturally produced in clinical workflows.

By Jonggwon Park, Seongeun Lee, Junhyun Park, Hannah Yun, Hyunwoong Kim, Sohyun Jeong, Hyewon Kang, Byungmu Yoon, Kyoyun Choi

llms rag computer-vision efficiency multimodal safety

arXiv Machine Learning

Jul 14

BiLoG-Net: A Bi-Context Location-Guided Network for Breast Mass Segmentation and Malignancy Classification in Mammography

arXiv:2607. 10188v1 Announce Type: cross Abstract: Breast cancer remains the most commonly diagnosed malignancy among women worldwide, yet accurate detection and characterization of breast masses in mammography remain challenging due to subtle intensity variations, heterogeneous tissue densities, and indistinct lesion boundaries that complicate radiological interpretation.

By Abu Fatema Mohammad Abdun Noor, Md Imam Ahasan, Md Samiul Ahasan, Kah Ong Michael Goh, S M Hasan Mahmud, Raihana Zannat

llms computer-vision benchmarks

arXiv Computer Vision

Sep 25

OncoVision: Integrating Mammography and Clinical Data through Attention-Driven Multimodal AI for Enhanced Breast Cancer Diagnosis

OncoVision is a privileged‑information training framework that learns from mammography images and clinical data during training but performs inference using only mammographic images. It employs an attention‑based encoder‑decoder to jointly segment masses, calcifications, axillary findings, and breast tissue, and predicts ten structured clinical features such as BI‑RADS. Two late‑fusion strategies (Independent and Dependent) integrate imaging, radiomic, and clinical information to improve diagnostic precision, and a retrospective multi‑reader study showed higher diagnostic confidence, reduced reading time, and segmentation accuracy comparable to or better than radiologists.

By Istiak Ahmed, Galib Ahmed, K. Shahriar Sanjid, Md. Tanzim Hossain, Md. Nishan Khan, Md. Misbah Khan, Md. Arifur Rahman, Sheikh Anisul Haque, Sharmin Akhtar Rupa, Mohammed Mejbahuddin Mia, Mahmud Hasan Mostofa Kamal, Md. Mostafa Kamal Sarker, M. Monir Uddin

computer-vision multimodal