arXiv Computer Vision August 27, 2026 By Aji Mao, Zhenming Peng, Bailin Mu, Tian Pu

SPARK-SAM: Learning How to Prompt and Respond for Infrared Small Target Segmentation

Read the original on arXiv Computer Vision →

SPARK‑SAM is a new approach that adapts the Segment‑Anything Model (SAM) for infrared small‑target segmentation by learning target‑domain response knowledge and conditioning the decoder with an image‑conditioned joint self‑prompt state. In experiments on three IRSTD benchmarks, SPARK‑SAM achieves IoU scores of 75.78%, 86.49%, and 68.34% with only 0.726 M additional parameters, outperforming 14 retrained SAM variants. The method combines benchmark‑mask supervision with reliability‑aware response guidance, and ablations show consistent accuracy gains from response guidance and high‑resolution prompt refinement.

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

Aug 24

SPARK-SAM: Self-Prompt Adaptation with Response Knowledge for SAM in Infrared Small Target Segmentation

arXiv:2608.20754v1 Announce Type: new Abstract: Promptable segmentation models provide a reusable interface, but direct transfer to automatic infrared small-target segmentation (IRSTD) exposes a mism...

By Aji Mao, Zhenming Peng, Bailin Mu, Tian Pu

computer-vision benchmarks data-engineering

arXiv AI

Aug 7

HyTBE: Hyperbolic Target-Background Expert Model for Cross-Domain Infrared Small Target Detection

arXiv:2608. 05771v1 Announce Type: cross Abstract: Infrared small target detection (IRSTD) has achieved substantial progress under domain-consistent evaluation, yet detector performance often degrades markedly when generalizing to unseen infrared domains.

By Aohua Li, Jin Kuang, Yubing Lu, Pingping Liu

arXiv Computation and Language

4d ago

From Routing Signals to Selective Review: Visual regrounding in MoE VLMs

arXiv:2609.38111v1 Announce Type: new Abstract: Vision-language models (VLMs) may accept false visual premises, answering questions about a target object's color, count, location, or state even when...

By Hongzhu Guo, Mohsen Fayyaz, Nanyun Peng

llms multimodal

Hugging Face Trending Papers

Jul 2

Boosting Infrared Small Target Detection via Logit-Domain Contrast and Adaptive Shape Refinement

Infrared small target detection (IRSTD) remains challenging due to tiny target size, low signal-to-noise ratio, severe foreground-background imbalance, and blurred boundaries in complex scenes. Existing methods usually rely on post-activation probability-domain supervision for discrimination, where weak targets and strong clutter may produce saturated and close probabilities, limiting weak-target discrimination.

diffusion

arXiv Computer Vision

Aug 28

DOD-SA: Infrared-Visible Decoupled Object Detection with Single-Modality Annotations

The paper introduces DOD-SA, a framework for infrared-visible object detection that uses only single-modality annotations. It employs a Collaborative Teacher-Student Network with a single-modality branch and a dual-modality decoupled branch to transfer knowledge across modalities, and a Progressive and Self‑Tuning Training Strategy to refine pseudo‑labels. A Pseudo Label Assigner is also designed to align labels between modalities during training.

By Hang Jin, Chenqiang Gao, Junjie Guo, Fangcen Liu, Qinyao Chang, Kanghui Tian, Deyu Meng

computer-vision

arXiv Machine Learning

Sep 11

Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language Models

The paper explores soft prompting for few‑shot object detection with vision‑language models, showing that optimizing a small number of continuous prompt tokens—especially when placed at the cross‑modal boundary and initialized from an empty space token—can match LoRA performance while training far fewer parameters. Soft prompting also avoids catastrophic forgetting, transfers to newer models, and can be verbalized into readable prompts. The study extends these findings to manipulation tasks, indicating that VLMs already contain much of the necessary knowledge for specialized domains, and the main challenge is learning how to ask for it.

By Gautam Rajendrakumar Gare, Siyi Li, Hewei Wang, Cesar Daniel Hernandez, Wei Zhao, Wolfgang M. Pauli, John Galeotti, Deva Ramanan

llms computer-vision robotics fine-tuning multimodal