Search Results for author:
Found 24 papers, 9 papers with code
HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness
First, inspired by these observations, we propose a simple yet effective data augmentation method HybridAugment that reduces the reliance of CNNs on high-frequency components, and thus improves their robustness while keeping their clean accuracy high.
VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON
We introduce the VISION Datasets, a diverse collection of 14 industrial inspection datasets, uniquely poised to meet these challenges.
Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection
Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and object detection.
Representation Recycling for Streaming Video Analysis
Our experiments on video semantic segmentation, video object detection, and human pose estimation in videos show that StreamDEQ achieves on-par accuracy with the baseline while being more than 2-4x faster.
Ranked #53 on
Semantic Segmentation
on Cityscapes val
How Robust are Discriminatively Trained Zero-Shot Learning Models?
In this paper, we present novel analyses on the robustness of discriminative ZSL to image corruptions.
Towards Zero-shot Sign Language Recognition
For this novel problem setup, we introduce three benchmark datasets with their accompanying textual and attribute descriptions to analyze the problem in detail.
MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation
To alleviate this need, we propose a self-supervised training approach for learning few-shot segmentation models.
Closed-form Sample Probing for Learning Generative Models in Zero-shot Learning
In our approach, at each generative model update step, we fit a task-specific closed-form ZSL model from generated samples, and measure its loss on novel samples all within the compute graph, a procedure that we refer to as sample probing.
Caption Generation on Scenes with Seen and Unseen Object Categories
For this problem, we propose a detection-driven approach that consists of a single-stage generalized zero-shot detection model to recognize and localize instances of both seen and unseen classes, and a template-based captioning model that transforms detections into sentences.
Weakly Supervised Instance Attention for Multisource Fine-Grained Object Recognition with an Application to Tree Species Classification
Multisource image analysis that leverages complementary spectral, spatial, and structural information benefits fine-grained object recognition that aims to classify an object into one of many similar subcategories.
Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos
To mimic such scenarios, we formulate a realistic domain-transfer problem, where the goal is to transfer the recognition model trained on clean posed images to the target domain of violent videos, where training videos are available only for a subset of subjects.
A Deep Dive into Adversarial Robustness in Zero-Shot Learning
In constrast, Zero-shot Learning (ZSL) and Generalized Zero-shot Learning (GZSL) tasks inherently lack supervision across all classes.
Image Captioning with Unseen Objects
Image caption generation is a long standing and challenging problem at the intersection of computer vision and natural language processing.
Zero-Shot Sign Language Recognition: Can Textual Data Uncover Sign Languages?
We introduce the problem of zero-shot sign language recognition (ZSSLR), where the goal is to leverage models learned over the seen sign class examples to recognize the instances of unseen signs.
Learning Visually Consistent Label Embeddings for Zero-Shot Learning
In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end manner.
Cross-task weakly supervised learning from instructional videos
In this paper we investigate learning visual models for the steps of ordinary tasks using weak supervision via instructional narrations and an ordered list of steps instead of strong supervision via temporal annotations.
Ranked #5 on
Temporal Action Localization
on CrossTask
Multisource Region Attention Network for Fine-Grained Object Recognition in Remote Sensing Imagery
Fine-grained object recognition concerns the identification of the type of an object among a large number of closely related sub-categories.
Wildest Faces: Face Detection and Recognition in Violent Settings
With the introduction of large-scale datasets and deep learning models capable of learning complex representations, impressive advances have emerged in face detection and recognition tasks.
Zero-Shot Object Detection by Hybrid Region Embedding
Object detection is considered as one of the most challenging problems in computer vision, since it requires correct prediction of both classes and locations of objects in images.
Ranked #7 on
Zero-Shot Object Detection
on PASCAL VOC'07
Fine-Grained Object Recognition and Zero-Shot Learning in Remote Sensing Imagery
Fine-grained object recognition that aims to identify the type of an object among a large number of subcategories is an emerging application with the increasing resolution that exposes new details in image data.
Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names.
Approximate Fisher Kernels of non-iid Image Models for Image Categorization
It has been experimentally observed that the performance of BoW and FV representations can be improved by employing discounting transformations such as power normalization.
Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning
In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations.
Multi-fold MIL Training for Weakly Supervised Object Localization
In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations.
