Cover Image

LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Aminbeidokhti, Masih, Roy, Subhankar, Granger, Eric, Ricci, Elisa, Pedersoli, Marco
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Revisiting Mixout: An Overlooked Path to Robust Finetuning
by: Aminbeidokhti, Masih, et al.
Published: (2025)

Source-Free Domain Adaptation for YOLO Object Detection
by: Varailhon, Simon, et al.
Published: (2024)

High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization
by: Aminbeidokhti, Masih, et al.
Published: (2025)

Domain Generalization by Rejecting Extreme Augmentations
by: Aminbeidokhti, Masih, et al.
Published: (2023)

Infrared Object Detection with Ultra Small ConvNets: Is ImageNet Pretraining Still Useful?
by: Muralidharan, Srikanth, et al.
Published: (2025)

RADIN: Souping on a Budget
by: Menes, Thibaut, et al.
Published: (2024)

WiSE-OD: Benchmarking Robustness in Infrared Object Detection
by: Medeiros, Heitor R., et al.
Published: (2025)

WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average
by: Fournier, Louis, et al.
Published: (2024)

How (Mis)calibrated is Your Federated CLIP and What To Do About It?
by: Singha, Mainak, et al.
Published: (2025)

Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
by: Belal, Atif, et al.
Published: (2024)

Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
by: Liu, Mingxuan, et al.
Published: (2023)

A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
by: Murtaza, Shakeeb, et al.
Published: (2024)

Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos
by: Murtaza, Shakeeb, et al.
Published: (2024)

Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
by: Gabetni, Firas, et al.
Published: (2025)

Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge
by: Medeiros, Heitor Rapela, et al.
Published: (2024)

TeD-Loc: Text Distillation for Weakly Supervised Object Localization
by: Murtaza, Shakeeb, et al.
Published: (2025)

HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information
by: Medeiros, Heitor Rapela, et al.
Published: (2023)

Diffusion Soup: Model Merging for Text-to-Image Diffusion Models
by: Biggs, Benjamin, et al.
Published: (2024)

Spatial Action Unit Cues for Interpretable Deep Facial Expression Recognition
by: Belharbi, Soufiane, et al.
Published: (2024)

Leveraging Model Soups to Classify Intangible Cultural Heritage Images from the Mekong Delta
by: Tran, Quoc-Khang, et al.
Published: (2026)

Visual Modality Prompt for Adapting Vision-Language Object Detectors
by: Medeiros, Heitor R., et al.
Published: (2024)

DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification
by: Tojo, Kenji, et al.
Published: (2026)

Fast View Synthesis of Casual Videos with Soup-of-Planes
by: Lee, Yao-Chih, et al.
Published: (2023)

Adversarial Example Soups: Improving Transferability and Stealthiness for Free
by: Yang, Bo, et al.
Published: (2024)

BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change
by: González-González, Manuela, et al.
Published: (2025)

DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
by: Rangwani, Harsh, et al.
Published: (2024)

Deep Attention-guided Adaptive Subsampling
by: Shankaranarayana, Sharath M, et al.
Published: (2025)

Context-Aware Sensor Modeling for Asynchronous Multi-Sensor Tracking in Stone Soup
by: Larsen, Martin Vonheim, et al.
Published: (2026)

VLOD-TTA: Test-Time Adaptation of Vision-Language Object Detectors
by: Belal, Atif, et al.
Published: (2025)

MiPa: Mixed Patch Infrared-Visible Modality Agnostic Object Detection
by: Medeiros, Heitor R., et al.
Published: (2024)

Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling
by: Bouayed, Aymene Mohammed, et al.
Published: (2025)

Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues
by: Belharbi, Soufiane, et al.
Published: (2024)

CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos
by: Belharbi, Soufiane, et al.
Published: (2023)

Clean-GS: Semantic Mask-Guided Pruning for 3D Gaussian Splatting
by: Mishra, Subhankar
Published: (2026)

Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning
by: Qi, Zhi-Hong, et al.
Published: (2024)

Joint Multimodal Transformer for Emotion Recognition in the Wild
by: Waligora, Paul, et al.
Published: (2024)

Multi Teacher Privileged Knowledge Distillation for Multimodal Expression Recognition
by: Aslam, Muhammad Haseeb, et al.
Published: (2024)

Task Switching Without Forgetting via Proximal Decoupling
by: Shamsolmoali, Pourya, et al.
Published: (2026)

CAPT: Class-Aware Prompt Tuning for Federated Long-Tailed Learning with Vision-Language Model
by: Hou, Shihao, et al.
Published: (2025)

Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning
by: Feng, Shuai, et al.
Published: (2025)