no code implementations • 15 Feb 2025 • Md Yousuf Harun, Jhair Gallardo, Christopher Kanan
In experiments, our method excels at both tasks across OOD datasets and DNN architectures.
no code implementations • 2 Dec 2024 • Wenbo Zhang, Junyu Chen, Christopher Kanan
Due to their large sizes, volumetric scans and whole-slide pathology images (WSIs) are often processed by extracting embeddings from local regions and then an aggregator makes predictions from this set.
no code implementations • 25 Oct 2024 • Shikhar Srivastava, Md Yousuf Harun, Robik Shrestha, Christopher Kanan
However, this integration often significantly decreases performance on natural language understanding and generation tasks, compared to the original LLM.
no code implementations • 13 Sep 2024 • Rahman Ejaz, Varchas Gopalaswamy, Riccardo Betti, Aarne Lees, Christopher Kanan
In this work, focusing on nuclear fusion energy using high powered lasers, we present the use of Kolmogorov-Arnold Networks (KANs) as an alternative to PIL for developing a new type of data-driven predictive model which is able to achieve high prediction accuracy and physics interpretability.
no code implementations • 9 Aug 2024 • Jian Lu, Shikhar Srivastava, Junyu Chen, Robik Shrestha, Manoj Acharya, Kushal Kafle, Christopher Kanan
With the advent of multi-modal large language models (MLLMs), datasets used for visual question answering (VQA) and referring expression comprehension have seen a resurgence.
no code implementations • 23 May 2024 • Md Yousuf Harun, Kyungbok Lee, Jhair Gallardo, Giri Krishnan, Christopher Kanan
We study the factors influencing transferability and out-of-distribution (OOD) generalization of pre-trained DNN embeddings through the lens of the tunnel effect hypothesis, which is closely related to intermediate neural collapse.
2 code implementations • 16 May 2024 • George Shaikovski, Adam Casson, Kristen Severson, Eric Zimmermann, Yi Kan Wang, Jeremy D. Kunz, Juan A. Retamero, Gerard Oakley, David Klimstra, Christopher Kanan, Matthew Hanna, Michal Zelechowski, Julian Viret, Neil Tenenholtz, James Hall, Nicolo Fusi, Razik Yousfi, Peter Hamilton, William A. Moye, Eugene Vorontsov, SiQi Liu, Thomas J. Fuchs
Foundation models in computational pathology promise to unlock the development of new clinical decision support systems and models for precision medicine.
no code implementations • 22 Dec 2023 • Chen Ding, Christopher Kanan, Dylan McKellips, Toranosuke Ozawa, Arian Shahmirza, Wesley Smith
The greatest demand for today's computing is machine learning.
no code implementations • 20 Dec 2023 • Yunye Gong, Robik Shrestha, Jared Claypoole, Michael Cogswell, Arijit Ray, Christopher Kanan, Ajay Divakaran
We propose a novel VQA dataset, BloomVQA, to facilitate comprehensive evaluation of large vision-language models on comprehension tasks.
no code implementations • 20 Nov 2023 • Eli Verwimp, Rahaf Aljundi, Shai Ben-David, Matthias Bethge, Andrea Cossu, Alexander Gepperth, Tyler L. Hayes, Eyke Hüllermeier, Christopher Kanan, Dhireesha Kudithipudi, Christoph H. Lampert, Martin Mundt, Razvan Pascanu, Adrian Popescu, Andreas S. Tolias, Joost Van de Weijer, Bing Liu, Vincenzo Lomonaco, Tinne Tuytelaars, Gido M. van de Ven
Continual learning is a subfield of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past.
1 code implementation • 14 Sep 2023 • Eugene Vorontsov, Alican Bozkurt, Adam Casson, George Shaikovski, Michal Zelechowski, SiQi Liu, Kristen Severson, Eric Zimmermann, James Hall, Neil Tenenholtz, Nicolo Fusi, Philippe Mathieu, Alexander van Eck, Donghun Lee, Julian Viret, Eric Robert, Yi Kan Wang, Jeremy D. Kunz, Matthew C. H. Lee, Jan Bernhard, Ran A. Godrich, Gerard Oakley, Ewan Millar, Matthew Hanna, Juan Retamero, William A. Moye, Razik Yousfi, Christopher Kanan, David Klimstra, Brandon Rothrock, Thomas J. Fuchs
The use of artificial intelligence to enable precision medicine and decision support systems through the analysis of pathology images has the potential to revolutionize the diagnosis and treatment of cancer.
Ranked #1 on
Breast Tumour Classification
on PCam
(Accuracy metric, using extra
training data)
no code implementations • 25 Aug 2023 • Md Yousuf Harun, Jhair Gallardo, Junyu Chen, Christopher Kanan
Compared to uniform balanced sampling, GRASP achieves the same performance with 40% fewer updates.
no code implementations • 9 Jun 2023 • Matthew Iceland, Christopher Kanan
Image Augmentations are widely used to reduce overfitting in neural networks.
no code implementations • 2 Jun 2023 • Md Yousuf Harun, Christopher Kanan
We identify the "stability gap" as a major obstacle in our setting.
no code implementations • 8 May 2023 • Junyu Chen, Jie An, Hanjia Lyu, Christopher Kanan, Jiebo Luo
Assessing the artness of AI-generated images continues to be a challenge within the realm of image generation.
no code implementations • 29 Mar 2023 • Md Yousuf Harun, Jhair Gallardo, Tyler L. Hayes, Christopher Kanan
There is more to continual learning than mitigating catastrophic forgetting.
1 code implementation • 19 Mar 2023 • Md Yousuf Harun, Jhair Gallardo, Tyler L. Hayes, Ronald Kemker, Christopher Kanan
Compared to REMIND and prior arts, SIESTA is far more computationally efficient, enabling continual learning on ImageNet-1K in under 2 hours on a single GPU; moreover, in the augmentation-free setting it matches the performance of the offline learner, a milestone critical to driving adoption of continual learning in real-world applications.
no code implementations • 8 Dec 2022 • Indranil Sur, Zachary Daniels, Abrar Rahman, Kamil Faber, Gianmarco J. Gallardo, Tyler L. Hayes, Cameron E. Taylor, Mustafa Burak Gurbuz, James Smith, Sahana Joshi, Nathalie Japkowicz, Michael Baron, Zsolt Kira, Christopher Kanan, Roberto Corizzo, Ajay Divakaran, Michael Piacentino, Jesse Hostetler, Aswin Raghavan
In this paper, we introduce the Lifelong Reinforcement Learning Components Framework (L2RLCF), which standardizes L2RL systems and assimilates different continual learning components (each addressing different aspects of the lifelong learning problem) into a unified system.
1 code implementation • 23 Nov 2022 • Junyu Chen, Jie An, Hanjia Lyu, Christopher Kanan, Jiebo Luo
Visual-textual sentiment analysis aims to predict sentiment with the input of a pair of image and text, which poses a challenge in learning effective features for diverse input images.
no code implementations • 16 Oct 2022 • Aneesh Rangnekar, Christopher Kanan, Matthew Hoffman
We achieve more than 95% of the network's performance on CamVid and CityScapes datasets, utilizing only 12. 1% and 15. 1% of the labeled data, respectively.
1 code implementation • 4 May 2022 • Rakshit S. Kothari, Reynold J. Bailey, Christopher Kanan, Jeff B. Pelz, Gabriel J. Diaz
Previous work has shown that convolutional networks excel at extracting gaze features despite the presence of such artifacts.
1 code implementation • 5 Apr 2022 • Robik Shrestha, Kushal Kafle, Christopher Kanan
We propose a new direction: modifying the network architecture to impose inductive biases that make the network robust to dataset bias.
Ranked #3 on
Action Recognition
on BAR
no code implementations • 21 Mar 2022 • Aneesh Rangnekar, Christopher Kanan, Matthew Hoffman
Instead, our active learning approach aims to minimize the number of annotations per-image.
1 code implementation • 21 Mar 2022 • Tyler L. Hayes, Christopher Kanan
Real-time on-device continual learning is needed for new applications such as home robots, user personalization on smartphones, and augmented/virtual reality headsets.
no code implementations • 11 Mar 2022 • Tyler L. Hayes, Maximilian Nickel, Christopher Kanan, Ludovic Denoyer, Arthur Szlam
Using this framing, we introduce an active sampling method that asks for examples from the tail of the data distribution and show that it outperforms classical active learning methods on Visual Genome.
no code implementations • 11 Feb 2022 • Manoj Acharya, Anirban Roy, Kaushik Koneripalli, Susmit Jha, Christopher Kanan, Ajay Divakaran
GCRN consists of two separate graphs to predict object labels based on the contextual cues in the image: 1) a representation graph to learn object features based on the neighboring objects and 2) a context graph to explicitly capture contextual cues from the neighboring objects.
Ranked #1 on
Anomaly Detection
on COCO-OOC
no code implementations • 25 Oct 2021 • Manoj Acharya, Christopher Kanan
In this technical report, we present our approaches for the continual object detection track of the SODA10M challenge.
no code implementations • 2 Jul 2021 • YiPeng Zhang, Tyler L. Hayes, Christopher Kanan
Humans are incredibly good at transferring knowledge from one domain to another, enabling rapid learning of new tasks.
no code implementations • 29 Jun 2021 • Bidur Khanal, Christopher Kanan
Incorrectly labeled examples, or label noise, is common in real-world computer vision datasets.
no code implementations • 1 Apr 2021 • Tyler L. Hayes, Giri P. Krishnan, Maxim Bazhenov, Hava T. Siegelmann, Terrence J. Sejnowski, Christopher Kanan
Replay is the reactivation of one or more neural patterns, which are similar to the activation patterns experienced during past waking experiences.
4 code implementations • 1 Apr 2021 • Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu, Antonio Carta, Gabriele Graffieti, Tyler L. Hayes, Matthias De Lange, Marc Masana, Jary Pomponi, Gido van de Ven, Martin Mundt, Qi She, Keiland Cooper, Jeremy Forest, Eden Belouadah, Simone Calderara, German I. Parisi, Fabio Cuzzolin, Andreas Tolias, Simone Scardapane, Luca Antiga, Subutai Amhad, Adrian Popescu, Christopher Kanan, Joost Van de Weijer, Tinne Tuytelaars, Davide Bacciu, Davide Maltoni
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning.
1 code implementation • 1 Apr 2021 • Robik Shrestha, Kushal Kafle, Christopher Kanan
We introduce a new dataset called Biased MNIST that enables assessment of robustness to multiple bias sources.
no code implementations • 25 Mar 2021 • Jhair Gallardo, Tyler L. Hayes, Christopher Kanan
In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting.
1 code implementation • 6 Mar 2021 • Tyler L. Hayes, Christopher Kanan
Analogical reasoning tests such as Raven's Progressive Matrices (RPMs) are commonly used to measure non-verbal abstract reasoning in humans, and recently offline neural networks for the RPM problem have been proposed.
no code implementations • 4 Mar 2021 • Usman Mahmood, Robik Shrestha, David D. B. Bates, Lorenzo Mannelli, Giuseppe Corrias, Yusuf Erdi, Christopher Kanan
Artificial intelligence (AI) has been successful at solving numerous problems in machine perception.
no code implementations • 10 Sep 2020 • Ryne Roady, Tyler L. Hayes, Christopher Kanan
Supervised classification methods often assume that evaluation data is drawn from the same distribution as training data and that all classes are present for training.
1 code implementation • 14 Aug 2020 • Manoj Acharya, Tyler L. Hayes, Christopher Kanan
Humans can incrementally learn to do new visual detection tasks, which is a huge challenge for today's computer vision systems.
1 code implementation • 14 Jun 2020 • Ryne Roady, Tyler L. Hayes, Hitesh Vaidya, Christopher Kanan
In this work, we introduce Stream-51, a new dataset for streaming classification consisting of temporally correlated images from 51 distinct object categories and additional evaluation classes outside of the training distribution to test novelty recognition.
no code implementations • NeurIPS 2020 • Damien Teney, Kushal Kafle, Robik Shrestha, Ehsan Abbasnejad, Christopher Kanan, Anton Van Den Hengel
Out-of-distribution (OOD) testing is increasingly popular for evaluating a machine learning system's ability to generalize beyond the biases of a training set.
no code implementations • 28 Apr 2020 • Zhongchao Qian, Tyler L. Hayes, Kushal Kafle, Christopher Kanan
Traditionally, deep convolutional neural networks consist of a series of convolutional and pooling layers followed by one or more fully connected (FC) layers to perform the final classification.
1 code implementation • ACL 2020 • Robik Shrestha, Kushal Kafle, Christopher Kanan
Existing Visual Question Answering (VQA) methods tend to exploit dataset biases and spurious statistical correlations, instead of producing right answers for the right reasons.
2 code implementations • 17 Dec 2019 • Aneesh Rangnekar, Nilay Mokashi, Emmett Ientilucci, Christopher Kanan, Matthew J. Hoffman
We investigate applying convolutional neural network (CNN) architecture to facilitate aerial hyperspectral scene understanding and present a new hyperspectral dataset-AeroRIT-that is large enough for CNN training.
no code implementations • 30 Oct 2019 • Ryne Roady, Tyler L. Hayes, Ronald Kemker, Ayesha Gonzales, Christopher Kanan
We found that input perturbation and temperature scaling yield the best performance on large scale datasets regardless of the feature space regularization strategy.
no code implementations • 28 Oct 2019 • Nabeel Seedat, Christopher Kanan
For many applications it is critical to know the uncertainty of a neural network's predictions.
1 code implementation • ECCV 2020 • Tyler L. Hayes, Kushal Kafle, Robik Shrestha, Manoj Acharya, Christopher Kanan
While there is neuroscientific evidence that the brain replays compressed memories, existing methods for convolutional networks replay raw images.
2 code implementations • 1 Oct 2019 • Aayush K. Chaudhary, Rakshit Kothari, Manoj Acharya, Shusil Dangi, Nitinraj Nair, Reynold Bailey, Christopher Kanan, Gabriel Diaz, Jeff B. Pelz
Accurate eye segmentation can improve eye-gaze estimation and support interactive computing based on visual attention; however, existing eye segmentation methods suffer from issues such as person-dependent accuracy, lack of robustness, and an inability to be run in real-time.
Ranked #1 on
Semantic Segmentation
on OpenEDS
2 code implementations • 4 Sep 2019 • Tyler L. Hayes, Christopher Kanan
By combining streaming linear discriminant analysis with deep learning, we are able to outperform both incremental batch learning and streaming learning algorithms on both ImageNet ILSVRC-2012 and CORe50, a dataset that involves learning to classify from temporally ordered samples.
1 code implementation • 5 Aug 2019 • Kushal Kafle, Robik Shrestha, Brian Price, Scott Cohen, Christopher Kanan
Chart question answering (CQA) is a newly proposed visual question answering (VQA) task where an algorithm must answer questions about data visualizations, e. g. bar charts, pie charts, and line graphs.
no code implementations • 2 Jul 2019 • German I. Parisi, Christopher Kanan
Continual learning refers to the ability of a biological or artificial system to seamlessly learn from continuous streams of information while preventing catastrophic forgetting, i. e., a condition in which new incoming information strongly interferes with previously learned representations.
no code implementations • 9 May 2019 • Rakshit Kothari, Zhizhuo Yang, Christopher Kanan, Reynold Bailey, Jeff Pelz, Gabriel Diaz
Our approach was to collect a novel, naturalistic, and multimodal dataset of eye+head movements when subjects performed everyday tasks while wearing a mobile eye tracker equipped with an inertial measurement unit and a 3D stereo camera.
no code implementations • 19 Apr 2019 • Kushal Kafle, Robik Shrestha, Christopher Kanan
Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence.
no code implementations • NAACL 2019 • Manoj Acharya, Karan Jariwala, Christopher Kanan
We propose Visual Query Detection (VQD), a new visual grounding task.
Ranked #1 on
Referring Expression Comprehension
on VQDv1
2 code implementations • CVPR 2019 • Robik Shrestha, Kushal Kafle, Christopher Kanan
Visual Question Answering (VQA) research is split into two camps: the first focuses on VQA datasets that require natural image understanding and the second focuses on synthetic datasets that test reasoning.
1 code implementation • 29 Oct 2018 • Manoj Acharya, Kushal Kafle, Christopher Kanan
Most counting questions in visual question answering (VQA) datasets are simple and require no more than object detection.
Ranked #3 on
Object Counting
on HowMany-QA
1 code implementation • 16 Sep 2018 • Tyler L. Hayes, Nathan D. Cahill, Christopher Kanan
We find that full rehearsal can eliminate catastrophic forgetting in a variety of streaming learning settings, with ExStream performing well using far less memory and computation.
1 code implementation • 1 Apr 2018 • Ronald Kemker, Utsav B. Gewali, Christopher Kanan
Deep learning continues to push state-of-the-art performance for the semantic segmentation of color (i. e., RGB) imagery; however, the lack of annotated data for many remote sensing sensors (i. e. hyperspectral imagery (HSI)) prevents researchers from taking advantage of this recent success.
1 code implementation • 26 Mar 2018 • Ronald Kemker, Ryan Luu, Christopher Kanan
These low-shot learning frameworks will reduce the manual image annotation burden and improve semantic segmentation performance for remote sensing imagery.
no code implementations • 21 Feb 2018 • German I. Parisi, Ronald Kemker, Jose L. Part, Christopher Kanan, Stefan Wermter
Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan.
1 code implementation • CVPR 2018 • Kushal Kafle, Brian Price, Scott Cohen, Christopher Kanan
Bar charts are an effective way to convey numeric information, but today's algorithms cannot parse them.
no code implementations • 23 Dec 2017 • Aneesh Rangnekar, Nilay Mokashi, Emmett Ientilucci, Christopher Kanan, Matthew Hoffman
In contrast to the spectra of ground based images, aerial spectral images have low spatial resolution and suffer from higher noise interference.
no code implementations • ICLR 2018 • Ronald Kemker, Christopher Kanan
Arguably, the best method for incremental class learning is iCaRL, but it requires storing training examples for each class, making it challenging to scale.
no code implementations • 3 Nov 2017 • Dillon Graham, Seyed Hamed Fatemi Langroudi, Christopher Kanan, Dhireesha Kudithipudi
Analyzing spatio-temporal data like video is a challenging task that requires processing visual and temporal information effectively.
no code implementations • WS 2017 • Kushal Kafle, Mohammed Yousefhussien, Christopher Kanan
Data augmentation is widely used to train deep neural networks for image classification tasks.
no code implementations • 7 Aug 2017 • Ronald Kemker, Marc McClure, Angelina Abitino, Tyler Hayes, Christopher Kanan
Deep neural networks are used in many state-of-the-art systems for machine perception.
no code implementations • ICCV 2017 • Kushal Kafle, Christopher Kanan
As a result, evaluation scores are inflated and predominantly determined by answering easier questions, making it difficult to compare different methods.
1 code implementation • 19 Mar 2017 • Ronald Kemker, Carl Salvaggio, Christopher Kanan
In this paper, we adapt state-of-the-art DCNN frameworks in computer vision for semantic segmentation for MSI imagery.
no code implementations • 6 Mar 2017 • Ronald Kemker, Carl Salvaggio, Christopher Kanan
Unmanned aircraft have decreased the cost required to collect remote sensing imagery, which has enabled researchers to collect high-spatial resolution data from multiple sensor modalities more frequently and easily.
no code implementations • 24 Nov 2016 • Sulabh Kumra, Christopher Kanan
In this paper, we present a novel robotic grasp detection system that predicts the best grasping pose of a parallel-plate robotic gripper for novel objects using the RGB-D image of the scene.
Ranked #4 on
Robotic Grasping
on Cornell Grasp Dataset
1 code implementation • 5 Oct 2016 • Kushal Kafle, Christopher Kanan
We then exhaustively review existing algorithms for VQA.
no code implementations • CVPR 2016 • Kushal Kafle, Christopher Kanan
Recently, algorithms for object recognition and related tasks have become sufficiently proficient that new vision tasks can now be pursued.