Herve Jegou

Neutral residues: revisiting adapters for model extension ICML 2025 Active Image Indexing ICLR 2023 Birth of a Transformer: A Memory Viewpoint NeurIPS 2023 Co-Training 2L Submodels for Visual Recognition CVPR 2023 Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models ICML 2023 The Stable Signature: Rooting Watermarks in Latent Diffusion Models ICCV 2023 DeiT III: Revenge of the ViT ECCV 2022 Three Things Everyone Should Know about Vision Transformers ECCV 2022 Emerging Properties in Self-Supervised Vision Transformers ICCV 2021 Going Deeper With Image Transformers ICCV 2021 Gradient-based Adversarial Attacks against Text Transformers EMNLP 2021 Grafit: Learning Fine-Grained Image Representations With Coarse Labels ICCV 2021 LeViT: A Vision Transformer in ConvNet's Clothing for Faster Inference ICCV 2021 Training data-efficient image transformers & distillation through attention ICML 2021 Training with Quantization Noise for Extreme Model Compression ICLR 2021 XCiT: Cross-Covariance Image Transformers NeurIPS 2021 And the Bit Goes Down: Revisiting the Quantization of Neural Networks ICLR 2020 Radioactive data: tracing through training ICML 2020 Equi-normalization of Neural Networks ICLR 2019 Fixing the train-test resolution discrepancy NeurIPS 2019 Large Memory Layers with Product Keys NeurIPS 2019 Spreading vectors for similarity search ICLR 2019 White-box vs Black-box: Bayes Optimal Strategies for Membership Inference ICML 2019 LAMV: Learning to Align and Match Videos With Kernelized Temporal Layers CVPR 2018 Link and Code: Fast Indexing With Graphs and Compact Regression Codes CVPR 2018 Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion EMNLP 2018 Low-Shot Learning With Large-Scale Diffusion CVPR 2018 Word translation without parallel data ICLR 2018 Efficient softmax approximation for GPUs ICML 2017 Early Burst Detection for Memory-Efficient Image Retrieval CVPR 2015 Action Localization with Tubelets from Motion CVPR 2014 Triangulation Embedding and Democratic Aggregation for Image Search CVPR 2014 Better Exploiting Motion for Better Action Recognition CVPR 2013 Event Retrieval in Large Video Collections with Circulant Temporal Encoding CVPR 2013 Query-Adaptive Asymmetrical Dissimilarities for Visual Object Retrieval ICCV 2013 Stable Hyper-pooling and Query Expansion for Event Detection ICCV 2013 To Aggregate or Not to aggregate: Selective Match Kernels for Image Search ICCV 2013