The dollar street dataset: Images representing the geographic and socioeconomic diversity of the world
It is crucial that image datasets for computer vision are representative and contain accurate
demographic information to ensure their robustness and fairness, especially for smaller …
demographic information to ensure their robustness and fairness, especially for smaller …
Webly supervised fine-grained recognition: Benchmark datasets and an approach
Learning from the web can ease the extreme dependence of deep learning on large-scale
manually labeled datasets. Especially for fine-grained recognition, which targets at …
manually labeled datasets. Especially for fine-grained recognition, which targets at …
Fine-grained recognition in the wild: A multi-task domain adaptation approach
While fine-grained object recognition is an important problem in computer vision, current
models are unlikely to accurately classify objects in the wild. These fully supervised models …
models are unlikely to accurately classify objects in the wild. These fully supervised models …
Learning expressive prompting with residuals for vision transformers
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. In this …
parameters into the input and intermediate representations of a pre-trained model. In this …
Benchmarking representation learning for natural world image collections
Recent progress in self-supervised learning has resulted in models that are capable of
extracting rich representations from image collections without requiring any explicit label …
extracting rich representations from image collections without requiring any explicit label …
Aerial images processing for car detection using convolutional neural networks: Comparison between faster r-cnn and yolov3
In this paper, we address the problem of car detection from aerial images using
Convolutional Neural Networks (CNN). This problem presents additional challenges as …
Convolutional Neural Networks (CNN). This problem presents additional challenges as …
Improving visual prompt tuning for self-supervised vision transformers
Abstract Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained
Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known …
Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known …
Detecting natural disasters, damage, and incidents in the wild
Responding to natural disasters, such as earthquakes, floods, and wildfires, is a laborious
task performed by on-the-ground emergency responders and analysts. Social media has …
task performed by on-the-ground emergency responders and analysts. Social media has …
Efficient adaptation of large vision transformer via adapter re-composing
W Dong, D Yan, Z Lin, P Wang - Advances in Neural …, 2024 - proceedings.neurips.cc
The advent of high-capacity pre-trained models has revolutionized problem-solving in
computer vision, shifting the focus from training task-specific models to adapting pre-trained …
computer vision, shifting the focus from training task-specific models to adapting pre-trained …
Pl@ ntNet-300K: a plant image dataset with high label ambiguity and a long-tailed distribution
This paper presents a novel image dataset with high intrinsic ambiguity and a longtailed
distribution built from the database of Pl@ ntNet citizen observatory. It consists of 306,146 …
distribution built from the database of Pl@ ntNet citizen observatory. It consists of 306,146 …