Cactus-Compute releases Mirage vision model on Hugging Face
Trending at number 30, the repo ships mirage.safetensors and mirage.cact, downloaded on first use.
Stories per day · 30 days
2 RSS
Relatedocr2vision-language2adversarial-patches1aerial-surveillance1autoregression1benchmark1cactus-compute1computer-vision1defect-detection1edge-ai1grounding1grounding-dino1huggingface1image-classification1image-encryption1industrial-vision1mllm1open-source1
14 stories, newest first · one card per story
Stories tagged #object-detection
Bottle-SKU benchmark and ProDMM target shampoo-bottle defects
The dataset has 13,119 images, 20,419 boxes, seven defect types, and 48 bottle SKUs.
Paper proposes Quaternion Approximate Networks for vision tasks
The authors report better accuracy with fewer parameters than prior convolution and quaternion models on standard vision benchmarks.
Category-selective encryption protects chosen objects in UAV imagery
An 80-class detector encrypts only user-specified categories, using thumbnail-preserving or XOR encryption.
WeVisOne-VL unifies object- and pixel-level visual perception
A pixel decoder behind an <OBJ> token emits boxes, masks, and mattes after curriculum SFT and mixed-task RL.
Edge vision-language models match detectors on physical patch evasion
A unified metric finds compact grounding VLMs can fail with confident wrong boxes, not only missed people.
WinARDet cuts repeated-box loops in dense vision-language grounding
On RSDense, authors report F1 rising from 32.16 to 39.36 and redundancy falling from 35.48% to 13.00%.
Supermarket Product Detection and Recognition: Utilizing Deep Learning with Rectified Imagery
Homography and Hough-based rectification improved grocery detection accuracy on angled supermarket images.
TrackFlood: Relocating Latency Attacks from NMS-Free Detectors to Real-Time Trackers
TrackFlood overloads real-time trackers behind NMS-free detectors, causing deadline misses at higher budgets.
ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus
ODPure purifies backdoor triggers in object detectors via corruption, reconstruction, and voting without discarding models.
GTR: Gated Token Recurrence for Efficient Dense Prediction
GTR introduces a softmax-free recurrent vision backbone reaching 58.9 box AP on COCO with sub-2ms latency, targeting high-resolution dense prediction and edge deployment.
Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection
Det-LIME extends LIME to multi-instance object detection explanations, improving attribution for harbor seal aerial surveys.
TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision
TAPe+ML v3 reaches 84.7 COCO detection mAP50 with under 100,000 parameters via a structured Theory of Active Perception representation.
Feature Recovery for Object Understanding After Irreversible Fire Damage
TRACE benchmark with 21.4K scenes studies post-fire object understanding; a Feature Recovery Module improves degraded-image retrieval by 12.5% and material recovery by 20.1%.