Yuki Markus Asano

CoRR, 2024

Foundation Model or Finetune? Evaluation of few-shot semantic segmentation for river pollution.

[BibT_eX]

[DOI]

Marga Don

Stijn Pinson

Blanca Guillen Cebrian

CoRR, 2024

NeCo: Improving DINOv2's spatial representations in 19 GPU hours with Patch Neighbor Consistency.

[BibT_eX]

[DOI]

CoRR, 2024

No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations.

[BibT_eX]

[DOI]

CoRR, 2024

Privacy-Aware Visual Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Bitune: Bidirectional Instruction-Tuning.

[BibT_eX]

[DOI]

Dawid Jan Kopiczko

Tijmen Blankevoort

Despina Ioanna Chalkiadaki

CoRR, 2024

Self-supervised visual learning in the low-data regime: a comparative evaluation.

[BibT_eX]

[DOI]

Sotirios Konstantakos

Ioannis Mademlis

Georgios Th. Papadopoulos

Efstratios Gavves

CoRR, 2024

DNA: Differentially private Neural Augmentation for contact tracing.

[BibT_eX]

[DOI]

CoRR, 2024

Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding.

[BibT_eX]

[DOI]

Babak Ehteshami Bejnordi

CoRR, 2024

The Common Stability Mechanism behind most Self-Supervised Learning Approaches.

[BibT_eX]

[DOI]

CoRR, 2024

Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video.

[BibT_eX]

[DOI]

Shashanka Venkataramanan

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Skip-Attention: Improving Vision Transformers by Paying Less Attention.

[BibT_eX]

[DOI]

Shashanka Venkataramanan

Proceedings of the Twelfth International Conference on Learning Representations, 2024

VeRA: Vector-based Random Matrix Adaptation.

[BibT_eX]

[DOI]

Dawid Jan Kopiczko

Tijmen Blankevoort

Proceedings of the Twelfth International Conference on Learning Representations, 2024

GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

SIGMA: Sinkhorn-Guided Masked Video Modeling.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

SelEx: Self-expertise in Fine-Grained Generalized Category Discovery.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Rethinking Image Super-Resolution from Training Data Perspectives.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Scaling Backwards: Minimal Synthetic Pre-Training?

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Object-Centric Diffusion for Efficient Video Editing.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Flow Matching for Conditional Text Generation in a Few Sampling Steps.

[BibT_eX]

[DOI]

Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, 2024

Federated Learning with a Single Shared Image.

[BibT_eX]

[DOI]

Sunny Soni

Aaqib Saeed

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Learning to Count Without Annotations.

[BibT_eX]

[DOI]

Lukas Knobel

Tengda Han

Tycho F. A. van der Ouderaa

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Protect Your Score: Contact-Tracing with Differential Privacy Guarantees.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

The LLM Surgeon.

[BibT_eX]

[DOI]

CoRR, 2023

Motion Flow Matching for Human Motion Synthesis and Editing.

[BibT_eX]

[DOI]

CoRR, 2023

VaLID: Variable-Length Input Diffusion for Novel View Synthesis.

[BibT_eX]

[DOI]

CoRR, 2023

Guided Diffusion from Self-Supervised Diffusion Features.

[BibT_eX]

[DOI]

CoRR, 2023

Self-Guided Open-Vocabulary Semantic Segmentation.

[BibT_eX]

[DOI]

CoRR, 2023

Small Visual Language Models can also be Open-Ended Few-Shot Learners.

[BibT_eX]

[DOI]

Mohammad Mahdi Derakhshani

CoRR, 2023

Semantic Counting from Self-Collages.

[BibT_eX]

[DOI]

Lukas Knobel

Tengda Han

CoRR, 2023

Towards Label-Efficient Incremental Learning: A Survey.

[BibT_eX]

[DOI]

Mert Kilickaya

Joost van de Weijer

CoRR, 2023

BISCUIT: Causal Representation Learning from Binary Interactions.

[BibT_eX]

[DOI]

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image.

[BibT_eX]

[DOI]

Aaqib Saeed

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Efficient Neural PDE-Solvers using Quantization Aware Training.

[BibT_eX]

[DOI]

Winfried van den Dool

Tijmen Blankevoort

Max Welling

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Self-Ordering Point Clouds.

[BibT_eX]

[DOI]

Pengwan Yang

Cees G. M. Snoek

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Self-Guided Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

No time to waste: practical statistical contact tracing with few low-bit messages.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Prompt Generation Networks for Efficient Adaptation of Frozen Vision Transformers.

[BibT_eX]

[DOI]

CoRR, 2022

Measuring the Interpretability of Unsupervised Representations via Quantized Reverse Probing.

[BibT_eX]

[DOI]

Iro Laina

CoRR, 2022

iCITRIS: Causal Representation Learning for Instantaneous Temporal Effects.

[BibT_eX]

[DOI]

CoRR, 2022

Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements.

[BibT_eX]

[DOI]

CoRR, 2022

CITRIS: Causal Identifiability from Temporal Intervened Sequences.

[BibT_eX]

[DOI]

CoRR, 2022

CITRIS: Causal Identifiability from Temporal Intervened Sequences.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing.

[BibT_eX]

[DOI]

Iro Laina

Proceedings of the Tenth International Conference on Learning Representations, 2022

Less Than Few: Self-shot Video Instance Segmentation.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

VTC: Improving Video-Text Retrieval with User Comments.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

Self-Supervised Learning of Object Parts for Semantic Segmentation.

[BibT_eX]

[DOI]

Adrian Ziegler

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Self-supervised object detection from audio-visual correspondence.

[BibT_eX]

[DOI]

Triantafyllos Afouras

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

Learning deep neural networks : necessity and scope of prior knowledge, raw data, and labels

[BibT_eX]

[DOI]

PhD thesis, 2021

Extrapolating from a Single Image to a Thousand Classes using Distillation.

[BibT_eX]

[DOI]

Aaqib Saeed

CoRR, 2021

Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset.

[BibT_eX]

[DOI]

CoRR, 2021

Privacy-preserving Object Detection.

[BibT_eX]

[DOI]

CoRR, 2021

How True is GPT-2? An Empirical Analysis of Intersectional Occupational Biases.

[BibT_eX]

[DOI]

CoRR, 2021

Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers.

[BibT_eX]

[DOI]

Christoph Feichtenhofer

João F. Henriques

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

PASS: An ImageNet replacement for self-supervised pretraining without humans.

[BibT_eX]

[DOI]

Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Support-set bottlenecks for video-text representation learning.

[BibT_eX]

[DOI]

Alexander G. Hauptmann

João F. Henriques

Proceedings of the 9th International Conference on Learning Representations, 2021

On Compositions of Transformations in Contrastive Self-Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020

Multi-modal Self-Supervision from Generalized Data Transformations.

[BibT_eX]

[DOI]

CoRR, 2020

Labelling unlabelled videos from scratch with multi-modal self-supervision.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Self-labelling via simultaneous clustering and representation learning.

[BibT_eX]

[DOI]

Christian Rupprecht

Proceedings of the 8th International Conference on Learning Representations, 2020

A critical analysis of self-supervision, or what we can learn from a single image.

[BibT_eX]

[DOI]

Christian Rupprecht

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Surprising Effectiveness of Few-Image Unsupervised Feature Learning.

[BibT_eX]

[DOI]

Christian Rupprecht