Search Results for author:
Found 24 papers, 7 papers with code
Few-shot adaptation for morphology-independent cell instance segmentation
Microscopy data collections are becoming larger and more frequent.
Current Topological and Machine Learning Applications for Bias Detection in Text
Institutional bias can impact patient outcomes, educational attainment, and legal system navigation.
ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos.
Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
Open-Fusion harnesses the power of a pre-trained vision-language foundation model (VLFM) for open-set semantic comprehension and employs the Truncated Signed Distance Function (TSDF) for swift 3D scene reconstruction.
SAM3D: Segment Anything Model in Volumetric Medical Images
Image segmentation remains a pivotal component in medical image analysis, aiding in the extraction of critical information for precise diagnostic practices.
Distributionally Robust Cross Subject EEG Decoding
In this work, we propose a principled approach to perform dynamic evolution on the data for improvement of decoding robustness.
ChatGPT in the Age of Generative AI and Large Language Models: A Concise Survey
We also lay out essential foundational literature on LLMs and GAI in general and their connection with ChatGPT.
More Synergy, Less Redundancy: Exploiting Joint Mutual Information for Self-Supervised Learning
This paper is a fundamental work where, we investigate role of mutual information in SSL, and reformulate the problem of SSL in the context of a new perspective on mutual information.
A Robust Likelihood Model for Novelty Detection
While this is a known problem that has been studied in recent years for the case of supervised learning, the case of novelty detection has received very limited attention.
Self-supervised Interest Point Detection and Description for Fisheye and Perspective Images
Keypoint detection and matching is a fundamental task in many computer vision problems, from shape reconstruction, to structure from motion, to AR/VR applications and robotics.
Z-GMOT: Zero-shot Generic Multiple Object Tracking
Our contributions are benchmarked through extensive experiments conducted on the Referring GMOT dataset for GMOT task.
Learning Representations for Masked Facial Recovery
The pandemic of these very recent years has led to a dramatic increase in people wearing protective masks in public venues.
CellTranspose: Few-shot Domain Adaptation for Cellular Instance Segmentation
Automated cellular instance segmentation is a process utilized for accelerating biological research for the past two decades, and recent advancements have produced higher quality results with less effort from the biologist.
Joint Discriminative and Metric Embedding Learning for Person Re-Identification
Person re-identification is a challenging task because of the high intra-class variance induced by the unrestricted nuisance factors of variations such as pose, illumination, viewpoint, background, and sensor noise.
FUSSL: Fuzzy Uncertain Self Supervised Learning
This double supervision approach is captured in two key steps: 1) invariance enforcement to data augmentation, and 2) fuzzy pseudo labeling (both hard and soft annotation).
Deep Active Ensemble Sampling For Image Classification
We show empirical results of our framework, and comparative performance with the state-of-the-art on four datasets, namely, MNIST, CIFAR10, CIFAR100 and ImageNet to establish a new baseline in two different settings.
Fine-Grained Visual Classification of Plant Species In The Wild: Object Detection as A Reinforced Means of Attention
Plant species identification in the wild is a difficult problem in part due to the high variability of the input data, but also because of complications induced by the long-tail effects of the datasets distribution.
Adversarial Latent Autoencoders
We designed two autoencoders: one based on a MLP encoder, and another based on a StyleGAN generator, which we call StyleALAE.
Ranked #5 on
Image Generation
on CelebA 256x256
(FID metric)
Generative Probabilistic Novelty Detection with Adversarial Autoencoders
We assume that training data is available to describe only the inlier distribution.
syGlass: Interactive Exploration of Multidimensional Images Using Virtual Reality Head-mounted Displays
The quest for deeper understanding of biological systems has driven the acquisition of increasingly larger multidimensional image datasets.
Few-Shot Adversarial Domain Adaptation
This work provides a framework for addressing the problem of supervised domain adaptation with deep models.
Unified Deep Supervised Domain Adaptation and Generalization
This work provides a unified framework for addressing the problem of visual supervised domain adaptation and generalization with deep models.
Ranked #87 on
Domain Generalization
on PACS
Information Bottleneck Learning Using Privileged Information for Visual Recognition
The problem is challenging because of the intrinsic asymmetry caused by the missing auxiliary view during testing.
A Supervised Low-Rank Method for Learning Invariant Subspaces
Sparse representation and low-rank matrix decomposition approaches have been successfully applied to several computer vision problems.
