no code implementations • ECCV 2020 • Qing Liu, Orchid Majumder, Alessandro Achille, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
This process enables incrementally improving the model by processing multiple learning episodes, each representing a different learning task, even with few training examples.
no code implementations • CVPR 2023 • Rajshekhar Das, Yonatan Dukler, Avinash Ravichandran, Ashwin Swaminathan
Prompt learning is an efficient approach to adapt transformers by inserting learnable set of parameters into the input and intermediate representations of a pre-trained model.
5 code implementations • CVPR 2023 • Jongheon Jeong, Yang Zou, Taewan Kim, Dongqing Zhang, Avinash Ravichandran, Onkar Dabeer
Visual anomaly classification and segmentation are vital for automating industrial quality inspection.
Ranked #9 on Anomaly Detection on VisA
no code implementations • CVPR 2023 • Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt Schiele, Ashwin Swaminathan, Stefano Soatto
The PPL improves the performance estimation on average by 37% across 16 classification and 33% across 10 detection datasets, compared to the power law.
no code implementations • 13 Sep 2022 • Achin Jain, Kibok Lee, Gurumurthy Swaminathan, Hao Yang, Bernt Schiele, Avinash Ravichandran, Onkar Dabeer
Combined with a matching loss, it can effectively find objects that are similar to the input patch and complete the missing annotations.
1 code implementation • 11 Aug 2022 • Zhaowei Cai, Avinash Ravichandran, Paolo Favaro, Manchen Wang, Davide Modolo, Rahul Bhotika, Zhuowen Tu, Stefano Soatto
We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks.
no code implementations • 3 Aug 2022 • Gukyeong Kwon, Zhaowei Cai, Avinash Ravichandran, Erhan Bas, Rahul Bhotika, Stefano Soatto
Instead of developing masked language modeling (MLM) and masked image modeling (MIM) independently, we propose to build joint masked vision and language modeling, where the masked signal of one modality is reconstructed with the help from another modality.
1 code implementation • 22 Jul 2022 • Kibok Lee, Hao Yang, Satyaki Chakraborty, Zhaowei Cai, Gurumurthy Swaminathan, Avinash Ravichandran, Onkar Dabeer
Most existing works on few-shot object detection (FSOD) focus on a setting where both pre-training and few-shot learning datasets are from a similar domain.
no code implementations • 12 Apr 2022 • Zhaowei Cai, Gukyeong Kwon, Avinash Ravichandran, Erhan Bas, Zhuowen Tu, Rahul Bhotika, Stefano Soatto
In this paper, we study the challenging instance-wise vision-language tasks, where the free-form language is required to align with the objects instead of the whole image.
1 code implementation • CVPR 2022 • Tz-Ying Wu, Gurumurthy Swaminathan, Zhizhong Li, Avinash Ravichandran, Nuno Vasconcelos, Rahul Bhotika, Stefano Soatto
We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations.
1 code implementation • CVPR 2022 • Matthew Wallingford, Hao Li, Alessandro Achille, Avinash Ravichandran, Charless Fowlkes, Rahul Bhotika, Stefano Soatto
TAPS solves a joint optimization problem which determines which layers to share with the base model and the value of the task-specific weights.
no code implementations • ICLR 2022 • Yonatan Dukler, Alessandro Achille, Giovanni Paolini, Avinash Ravichandran, Marzia Polito, Stefano Soatto
A learning task is a function from a training set to the validation error, which can be represented by a trained deep neural network (DNN).
no code implementations • 29 Sep 2021 • Zhizhong Li, Avinash Ravichandran, Charless Fowlkes, Marzia Polito, Rahul Bhotika, Stefano Soatto
Indeed, we observe experimentally that standard distillation of task-specific teachers, or using these teacher representations directly, **reduces** downstream transferability compared to a task-agnostic generalist model.
2 code implementations • NeurIPS 2021 • Sébastien M. R. Arnold, Guneet S. Dhillon, Avinash Ravichandran, Stefano Soatto
Episodic training is a core ingredient of few-shot learning to train models on tasks with limited labelled data.
no code implementations • 16 Jul 2021 • Zhizhong Li, Avinash Ravichandran, Charless Fowlkes, Marzia Polito, Rahul Bhotika, Stefano Soatto
Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher.
no code implementations • 29 Jan 2021 • Aditya Deshpande, Alessandro Achille, Avinash Ravichandran, Hao Li, Luca Zancato, Charless Fowlkes, Rahul Bhotika, Stefano Soatto, Pietro Perona
Since all model selection algorithms in the literature have been tested on different use-cases and never compared directly, we introduce a new comprehensive benchmark for model selection comprising of: i) A model zoo of single and multi-domain models, and ii) Many target tasks.
no code implementations • 26 Jan 2021 • Orchid Majumder, Avinash Ravichandran, Subhransu Maji, Alessandro Achille, Marzia Polito, Stefano Soatto
In this work we investigate the complementary roles of these two sources of information by combining instance-discriminative contrastive learning and supervised learning in a single framework called Supervised Momentum Contrastive learning (SUPMOCO).
1 code implementation • CVPR 2021 • Zhaowei Cai, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Zhuowen Tu, Stefano Soatto
We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher based self- and semi-supervised learning techniques.
Self-Supervised Learning Semi-Supervised Image Classification
1 code implementation • ICLR 2021 • Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
We define a notion of information that an individual sample provides to the training of a neural network, and we specialize it to measure both how much a sample informs the final weights and how much it informs the function computed by the weights.
no code implementations • CVPR 2021 • Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, Stefano Soatto
We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of remaining information after forgetting.
no code implementations • CVPR 2021 • Alessandro Achille, Aditya Golatkar, Avinash Ravichandran, Marzia Polito, Stefano Soatto
Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial conditions, and optimization.
no code implementations • NeurIPS 2020 • Luca Zancato, Alessandro Achille, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function.
1 code implementation • ICLR 2020 • Hao Li, Pratik Chaudhari, Hao Yang, Michael Lam, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
Our findings challenge common practices of fine-tuning and encourages deep learning practitioners to rethink the hyperparameters for fine-tuning.
no code implementations • 13 Feb 2020 • Xialei Liu, Hao Yang, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
For the difficult cases, where the domain gaps and especially category differences are large, we explore three different exemplar sampling methods and show the proposed adaptive sampling method is effective to select diverse and informative samples from entire datasets, to further prevent forgetting.
no code implementations • 11 Feb 2020 • Qing Liu, Orchid Majumder, Alessandro Achille, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large dataset and a testing phase, where the meta-learner leverages its learnt internal representation for a specific few-shot task involving classes which were not seen during the meta-training phase.
1 code implementation • 28 Nov 2019 • Istvan Fehervari, Avinash Ravichandran, Srikar Appalaraju
Deep metric learning (DML) is a popular approach for images retrieval, solving verification (same or not) problems and addressing open set classification.
3 code implementations • ICLR 2020 • Guneet S. Dhillon, Pratik Chaudhari, Avinash Ravichandran, Stefano Soatto
When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters.
no code implementations • ICCV 2019 • Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of ways and any number of shots (shot-free).
7 code implementations • CVPR 2019 • Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran, Stefano Soatto
We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks.
Ranked #12 on Few-Shot Image Classification on FC100 5-way (1-shot)
1 code implementation • ICCV 2019 • Alessandro Achille, Michael Lam, Rahul Tewari, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Stefano Soatto, Pietro Perona
We demonstrate that this embedding is capable of predicting task similarities that match our intuition about semantic and taxonomic relations between different visual tasks (e. g., tasks based on classifying different types of plants are similar) We also demonstrate the practical value of this framework for the meta-task of selecting a pre-trained feature extractor for a new task.
no code implementations • CVPR 2014 • Vasiliy Karasev, Avinash Ravichandran, Stefano Soatto
We describe an information-driven active selection approach to determine which detectors to deploy at which location in which frame of a video to minimize semantic class label uncertainty at every pixel, with the smallest computational cost that ensures a given uncertainty bound.