269 citations · 1k across the 33 of their papers we have counts for
36 papers
Whareformer: Learning to Track What is Where in Long Egocentric Videos
Jacob Chalk, Saptarshi Sinha, Dima Damen +2
The recently established 'Out of Sight, Not out of Mind' (OSNOM) task for egocentric videos focuses on tracking objects that are moved by the camera wearer, online, maintaining kno…
Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks
Pau de Jorge, César Roberto de Souza, Björn Michele +5
Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, m…
ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains
Pavel Suma, Giorgos Kordopatis-Zilos, Yannis Kalantidis +1
Large-scale instance-level training data is scarce, so models are typically trained on domain-specific datasets. Yet in real-world retrieval, they must handle diverse domains, maki…
DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
Mert Bulent Sariyildiz, Philippe Weinzaepfel, Thomas Lucas +3
Recent multi-teacher distillation methods have unified the encoders of multiple foundation models into a single encoder, achieving competitive performance on core vision tasks like…
LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
Vladan Stojnić, Yannis Kalantidis, Jiří Matas +1
We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs…
UNIC: Universal Classification Models via Multi-teacher Distillation
Mert Bulent Sariyildiz, Philippe Weinzaepfel, Thomas Lucas +2
Pretrained models have become a commodity and offer strong results on a broad range of tasks. In this work, we focus on classification and seek to learn a unique encoder able to ta…
Label Propagation for Zero-shot Classification with Vision-Language Models
Vladan Stojnić, Yannis Kalantidis, Giorgos Tolias
Vision-Language Models (VLMs) have demonstrated impressive performance on zero-shot classification, i.e. classification when provided merely with a list of class names. In this pap…
Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
Yannis Kalantidis, Mert Bülent Sarıyıldız, Rafael S. Rezende +3
State-of-the-art visual localization approaches generally rely on a first image retrieval step whose role is crucial. Yet, retrieval often struggles when facing varying conditions,…
Rethinking matching-based few-shot action recognition
Juliette Bertrand, Yannis Kalantidis, Giorgos Tolias
Few-shot action recognition, i.e. recognizing new action classes given only a few examples, benefits from incorporating temporal information. Prior work either encodes such informa…
Fake it till you make it: Learning transferable representations from synthetic ImageNet clones
Mert Bulent Sariyildiz, Karteek Alahari, Diane Larlus +1
Recent image generation models such as Stable Diffusion have exhibited an impressive ability to generate fairly realistic images starting from a simple text prompt. Could such mode…
Granularity-aware Adaptation for Image Retrieval over Multiple Tasks
Jon Almazán, Byungsoo Ko, Geonmo Gu +2
Strong image search models can be learned for a specific domain, ie. set of labels, provided that some labeled images of that domain are available. A practical visual search model,…
PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling
Fabien Baradel, Romain Brégier, Thibault Groueix +3
Training state-of-the-art models for human pose estimation in videos requires datasets with annotations that are really hard and expensive to obtain. Although transformers have bee…
No Reason for No Supervision: Improved Generalization in Supervised Models
Mert Bulent Sariyildiz, Yannis Kalantidis, Karteek Alahari +1
We consider the problem of training a deep neural network on a given classification task, e.g., ImageNet-1K (IN1K), so that it excels at both the training task as well as at other…
Learning Super-Features for Image Retrieval
Philippe Weinzaepfel, Thomas Lucas, Diane Larlus +1
Methods that combine local and global features have recently shown excellent performance on multiple challenging deep image retrieval benchmarks, but their use of local features ra…
Leveraging MoCap Data for Human Mesh Recovery
Fabien Baradel, Thibault Groueix, Philippe Weinzaepfel +3
Training state-of-the-art models for human body pose and shape recovery from images or videos requires datasets with corresponding annotations that are really hard and expensive to…
TLDR: Twin Learning for Dimensionality Reduction
Yannis Kalantidis, Carlos Lassance, Jon Almazan +1
Dimensionality reduction methods are unsupervised approaches which learn low-dimensional spaces where some properties of the initial space, typically the notion of "neighborhood",…
Probabilistic Embeddings for Cross-Modal Retrieval
Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio de Rezende +2
Cross-modal retrieval methods build a common representation space for samples from multiple modalities, typically from the vision and the language domains. For images and their cap…
Concept Generalization in Visual Representation Learning
Mert Bulent Sariyildiz, Yannis Kalantidis, Diane Larlus +1
Measuring concept generalization, i.e., the extent to which models trained on a set of (seen) visual concepts can be leveraged to recognize a new set of (unseen) concepts, is a pop…
Hard Negative Mixing for Contrastive Learning
Yannis Kalantidis, Mert Bulent Sariyildiz, Noe Pion +2
Contrastive learning has become a key component of self-supervised learning approaches for computer vision. By learning to embed two augmented versions of the same image close to e…
Proceedings of the ICLR Workshop on Computer Vision for Agriculture (CV4A) 2020
Yannis Kalantidis, Laura Sevilla-Lara, Ernest Mwebaze +3
This is the proceedings of the Computer Vision for Agriculture (CV4A) Workshop that was held in conjunction with the International Conference on Learning Representations (ICLR) 202…
Decoupling Representation and Classifier for Long-Tailed Recognition
Bingyi Kang, Saining Xie, Marcus Rohrbach +4
The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions…
Learning to Generate Grounded Visual Captions without Localization Supervision
Chih-Yao Ma, Yannis Kalantidis, Ghassan AlRegib +3
When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the…
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Yunpeng Chen, Haoqi Fan, Bing Xu +5
In natural images, information is conveyed at different frequencies where higher frequencies are usually encoded with fine details and lower frequencies are usually encoded with gl…
Less is More: Learning Highlight Detection from Video Duration
Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram +1
Highlight detection has the potential to significantly ease video browsing, but existing methods often suffer from expensive supervision requirements, where human viewers must manu…