Stefano Soatto

Scaling up Image Segmentation across Data and Tasks CVPR 2025 PICASO: Permutation-Invariant Context Composition with State Space Models ICLR 2025 Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding CVPR 2024 Enhancing Vision-Language Pre-training with Rich Supervisions CVPR 2024 WorDepth: Variational Language Prior for Monocular Depth Estimation CVPR 2024 THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models CVPR 2024 Non-autoregressive Sequence-to-Sequence Vision-Language Models CVPR 2024 Multi-Modal Hallucination Control by Visual Information Grounding CVPR 2024 On the Scalability of Diffusion-based Text-to-Image Generation CVPR 2024 RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions NIPS 2024 CPR: Retrieval Augmented Generation for Copyright Protection CVPR 2024 B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory NIPS 2024 Fewer Truncations Improve Language Modeling ICML 2024 Meaning Representations from Trajectories in Autoregressive Models ICLR 2024 Critical Learning Periods Emerge Even in Deep Linear Networks ICLR 2024 Tangent Transformers for Composition,Privacy and Removal ICLR 2024 DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models EMNLP 2024 AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation ECCV 2024 Diffusion Soup: Model Merging for Text-to-Image Diffusion Models ECCV 2024 On the Viability of Monocular Depth Pre-training for Semantic Segmentation ECCV 2024 Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation CVPR 2024 Sub-token ViT Embedding via Stochastic Resonance Transformers ICML 2024 Harnessing Unrecognizable Faces for Improving Face Recognition WACV 2023 Graph Spectral Embedding using the Geodesic Betweenness Centrality AISTATS 2023 Masked Vision and Language Modeling for Multi-modal Representation Learning ICLR 2023 Guided Recommendation for Model Fine-Tuning CVPR 2023 Train/Test-Time Adaptation With Retrieval CVPR 2023 A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting CVPR 2023 Gacs-Korner Common Information Variational Autoencoder NIPS 2023 A Meta-Learning Approach to Predicting Performance and Data Requirements CVPR 2023 Critical Learning Periods for Multisensory Integration in Deep Networks CVPR 2023 Tangent Model Composition for Ensembling and Continual Fine-tuning ICCV 2023 Linear Spaces of Meanings: Compositional Structures in Vision-Language Models ICCV 2023 SAFE: Machine Unlearning With Shard Graphs ICCV 2023 Your representations are in the network: composable and parallel adaptation for large scale models NIPS 2023 Leveraging sparse and shared feature activations for disentangled representation learning NIPS 2023 Depth Estimation From Camera Image and mmWave Radar Point Cloud CVPR 2023 On Leave-One-Out Conditional Mutual Information For Generalization NIPS 2022 Class-Incremental Learning With Strong Pre-Trained Models CVPR 2022 Task Adaptive Parameter Sharing for Multi-Task Learning CVPR 2022 DIVA: Dataset Derivative of a Learning Task ICLR 2022 MeMOT: Multi-Object Tracking With Memory CVPR 2022 Omni-DETR: Omni-Supervised Object Detection With Transformers CVPR 2022 Stereoscopic Universal Perturbations Across Different Architectures and Datasets CVPR 2022 X-DETR: A Versatile Architecture for Instance-Wise Vision-Language Tasks ECCV 2022 Not Just Streaks: Towards Ground Truth for Single Image Deraining ECCV 2022 Semi-supervised Vision Transformers at Scale NIPS 2022 Mixed Differential Privacy in Computer Vision CVPR 2022 ARCH++: Animation-Ready Clothed Human Reconstruction Revisited ICCV 2021 Long Short-Term Transformer for Online Action Detection NIPS 2021 Uniform Sampling over Episode Difficulty NIPS 2021 Exponential Moving Average Normalization for Self-Supervised and Semi-Supervised Learning CVPR 2021 Mixed-Privacy Forgetting in Deep Networks CVPR 2021 Compatibility-Aware Heterogeneous Visual Search CVPR 2021 LQF: Linear Quadratic Fine-Tuning CVPR 2021 Positive-Congruent Training: Towards Regression-Free Model Updates CVPR 2021 Dynamically Grown Generative Adversarial Networks AAAI 2021 Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates ACL 2021 Unsupervised Depth Completion With Calibrated Backprojection Layers ICCV 2021 Visual Relationship Detection Using Part-and-Sum Transformers With Composite Queries ICCV 2021 Estimating informativeness of samples with Smooth Unique Information ICLR 2021 Structured Prediction as Translation between Augmented Natural Languages ICLR 2021 DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping CVPR 2021 Learning Semantic-Aware Dynamics for Video Prediction CVPR 2021 Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations AAAI 2021 Learning Hierarchical Graph Neural Networks for Image Clustering ICCV 2021 Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates IJCNLP 2021 Rethinking the Hyperparameters for Fine-tuning ICLR 2020 Predicting Training Time Without Training NIPS 2020 Targeted Adversarial Perturbations for Monocular Depth Prediction NIPS 2020 Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction NIPS 2020 SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning CORL 2020 Zero Shot Learning with the Isoperimetric Loss AAAI 2020 FDA: Fourier Domain Adaptation for Semantic Segmentation CVPR 2020 Towards Backward-Compatible Representation Learning CVPR 2020 Learning to Manipulate Individual Objects in an Image CVPR 2020 Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks CVPR 2020 Phase Consistent Ecological Domain Adaptation CVPR 2020 Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment ECCV 2020 Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations ECCV 2020 A Baseline for Few-Shot Image Classification ICLR 2020 Meta-Q-Learning ICLR 2020 Few-Shot Learning With Embedded Class Models and Shot-Free Meta Training ICCV 2019 Unsupervised Domain Adaptation via Regularized Conditional Alignment ICCV 2019 Task2Vec: Task Embedding for Meta-Learning ICCV 2019 Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction CVPR 2019 Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence NIPS 2019 Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors AAAI 2019 Unsupervised Moving Object Detection via Contextual Information Separation CVPR 2019 GeoNet: Deep Geodesic Networks for Point Cloud Analysis CVPR 2019 Dense Depth Posterior (DDP) From Single Image and Sparse Range CVPR 2019 Critical Learning Periods in Deep Networks ICLR 2019 Meta-Learning With Differentiable Convex Optimization CVPR 2019 Emergence of Invariance and Disentanglement in Deep Representations JMLR 2018 Empirical Study of the Topology and Geometry of Deep Networks CVPR 2018 OATM: Occlusion Aware Template Matching by Consensus Set Maximization CVPR 2018 Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification ECCV 2018 Visual-Inertial Object Detection and Mapping ECCV 2018 Conditional Prior Networks for Optical Flow ECCV 2018 Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks ICLR 2018 Robustness of Classifiers to Universal Perturbations: A Geometric Perspective ICLR 2018 SaaS: Speed as a Supervisor for Semi-supervised Learning ECCV 2018 Visual-Inertial-Semantic Scene Representation for 3D Object Detection CVPR 2017 Zero Shot Learning via Multi-Scale Manifold Regularization CVPR 2017 S2F: Slow-To-Fast Interpolator Flow CVPR 2017 An Empirical Evaluation of Current Convolutional Architectures' Ability to Manage Nuisance Location and Scale Variability CVPR 2016 Observability, Identifiability and Sensitivity of Vision-Aided Inertial Navigation IJCAI 2016 Texture Representations for Image and Video Synthesis CVPR 2015 Self-Occlusions and Disocclusions in Causal Video Object Segmentation ICCV 2015 Domain-Size Pooling in Local Descriptors: DSP-SIFT CVPR 2015 Causal Video Object Segmentation From Persistence of Occlusions CVPR 2015 Multi-View Feature Engineering and Learning CVPR 2015 Efficient Minimal-Surface Regularization of Perspective Depth Maps in Variational Stereo CVPR 2015 Second-Order Shape Optimization for Geometric Inverse Problems in Vision CVPR 2014 Asymmetric Sparse Kernel Approximations for Large-scale Visual Search CVPR 2014 Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation CVPR 2014 CLAM: Coupled Localization and Mapping with Efficient Outlier Handling CVPR 2013 Nonlinearly Constrained MRFs: Exploring the Intrinsic Dimensions of Higher-Order Cliques CVPR 2013 Controlled Recognition Bounds for Visual Learning and Exploration NIPS 2012 Multiple Instance Filtering NIPS 2011 Occlusion Detection and Motion Estimation with Convex Optimization NIPS 2010 A Complexity-Distortion Approach to Joint Pattern Alignment NIPS 2006 Detecting Humans via Their Pose NIPS 2006