相关论文: Bugs in the Data: How ImageNet Misrepresents Biodi…

The main challenge in applying state-of-the-art deep learning methods to predict image quality in-the-wild is the relatively small size of existing quality scored datasets. The reason for the lack of larger datasets is the massive resources…

Despite the transformative potential of AI, the concept of neural networks that can produce other neural networks by generating model weights (hypernetworks) has been largely understudied. One of the possible reasons is the lack of…

Does progress on ImageNet transfer to real-world datasets? We investigate this question by evaluating ImageNet pre-trained models with varying accuracy (57% - 83%) on six practical image classification datasets. In particular, we study…

Many advances of deep learning techniques originate from the efforts of addressing the image classification task on large-scale datasets. However, the construction of such clean datasets is costly and time-consuming since the Internet is…

Global biodiversity is declining at an unprecedented rate, yet little information is known about most species and how their populations are changing. Indeed, some 90% of Earth's species are estimated to be completely unknown. Machine…

Millions of stray animals suffer on the streets or are euthanized in shelters every day around the world. In order to better adopt stray animals, scoring the pawpularity (cuteness) of stray animals is very important, but evaluating the…

Localizing and counting large ungulates -- hoofed mammals like cows and elk -- in very high-resolution satellite imagery is an important task for supporting ecological studies. Prior work has shown that this is feasible with deep learning…

Computer vision technology is being used by many but remains representative of only a few. People have reported misbehavior of computer vision models, including offensive prediction results and lower performance for underrepresented groups.…

Accurate identification of crop and weed species is critical for precision agriculture and sustainable farming. However, it remains a challenging task due to a variety of factors -- a high degree of visual similarity among species,…

Automatic species classification in camera traps would greatly help the biodiversity monitoring and species analysis in the earth. In order to accelerate the development of automatic species classification task, "Microsoft AI for Earth"…

Currently, data and model size dominate the narrative in the training of super-large, powerful models. However, there has been a lack of exploration on the effect of other attributes of the training dataset on model performance. We…

Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the…

Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild. Despite their ubiquity in the real-world deployments,…

The management of natural environments, whether for conservation or production, requires a deep understanding of wildlife. The number, location, and behavior of wild animals are among the main subjects of study in ecology and wildlife…

In existing visual representation learning tasks, deep convolutional neural networks (CNNs) are often trained on images annotated with single tags, such as ImageNet. However, a single tag cannot describe all important contents of one image,…

Recognising animals based on distinctive body patterns, such as stripes, spots, or other markings, in night images is a complex task in computer vision. Existing methods for detecting animals in images often rely on colour information,…

Machine learning (ML) approaches are used more and more widely in biodiversity monitoring. In particular, an important application is the problem of predicting biodiversity indicators such as species abundance, species occurrence or species…

Recent work has established the ecological importance of developing algorithms for identifying animals individually from images. Typically, a separate algorithm is trained for each species, a natural step but one that creates significant…

Deep learning vision systems are widely deployed across applications where reliability is critical. However, even today's best models can fail to recognize an object when its pose, lighting, or background varies. While existing benchmarks…

The keep-growing content of Web images may be the next important data source to scale up deep neural networks, which recently obtained a great success in the ImageNet classification challenge and related tasks. This prospect, however, has…