Description
Book Synopsis.- DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal.
.- Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models.
.- Aligning Vision Language Models with Contrastive Learning.
.- Open-set object detection: towards unified problem formulation and benchmarking.
.- Open-Vocabulary Object Detectors: Robustness Challenges under Distribution Shifts.
.- SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic Segmentation.
.- Online Stochastic Optimization for Data with Temporal Dependencies.
.- A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models.
.- OSSA: Unsupervised One-Shot Style Adaptation.
.- ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer.
.- Open-set Plankton Recognition.
.- Do Vision Foundation Models Enhance Domain Generalization in Medical Image Segmentation?.
.- On the Potential of Open-Vocabulary Models for Object Detection in Unusual Street Scenes.
.- Source-Free Domain Adaptation for YOLO Object Detection.
.- Task-Specific Adaptation of Segmentation Foundation Model via Prompt Learning.
.- Utilizing Class-Agnostic Point-to-Box Regressors as Object Proposal Generators.
.- Introducing a Class-Aware Metric for Monocular Depth Estimation: An Automotive Perspective.
.- Improving Generalization in Visual Reasoning via Self-Ensemble.
.- BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentation.
.- Image Translation with Kernel Prediction Networks for Semantic Segmentation.
.- Robust fine-tuning and adaptation of zero-shot models via adaptive weightspace ensembling.
.- Robustness to Spurious Correlation: A Comprehensive Review.
