( events)   Timezone: »  
Mon Dec 13 04:00 AM -- 05:15 PM (PST)
ImageNet: Past, Present, and Future
Zeynep Akata · Lucas Beyer · Sanghyuk Chun · A. Sophia Koepke · Diane Larlus · Seong Joon Oh · Rafael Rezende · Sangdoo Yun · Xiaohua Zhai

Since its release in 2010, ImageNet has played an instrumental role in the development of deep learning architectures for computer vision, enabling neural networks to greatly outperform hand-crafted visual representations. ImageNet also quickly became the go-to benchmark for model architectures and training techniques which eventually reach far beyond image classification. Today’s models are getting close to “solving” the benchmark. Models trained on ImageNet have been used as strong initialization for numerous downstream tasks. The ImageNet dataset has even been used for tasks going way beyond its initial purpose of training classification model. It has been leveraged and reinvented for tasks such as few-shot learning, self-supervised learning and semi-supervised learning. Interesting re-creation of the ImageNet benchmark enables the evaluation of novel challenges like robustness, bias, or concept generalization. More accurate labels have been provided. About 10 years later, ImageNet symbolizes a decade of staggering advances in computer vision, deep learning, and artificial intelligence.

We believe now is a good time to discuss what’s next: Did we solve ImageNet? What are the main lessons learnt thanks to this benchmark? What should the next generation of ImageNet-like benchmarks encompass? Is language supervision a promising alternative? How can we reflect on the diverse requirements for good datasets and models, such as fairness, privacy, security, generalization, scale, and efficiency?

Opening (Opening presentation)
Fairness and privacy aspects of ImageNet (Talk)
OpenImages: One Dataset for Many Computer Vision Tasks (Talk)
Object recognition in machines and brains (Talk)
Live panel: The future of ImageNet (Live panel)
Spotlight talk: ResNet strikes back: An improved training procedure in timm. (Oral session)
Poster session A (Poster session)
Is ImageNet Solved? Evaluating Machine Accuracy (Talk)
From ImageNet to Image Classification (Talk)
Are we done with ImageNet? (Talk)
Live panel: Did we solve ImageNet? (Live panel)
Uncovering the Deep Unknowns of ImageNet Model: Challenges and Opportunties (Talk)
ImageNet models from the trenches (Talk)
Using ImageNet to Measure Robustness and Uncertainty (Talk)
Live panel: Perspectives on ImageNet. (Live panel)
ImageNets of "x": ImageNet's Infrastructural Impact (Talk)
Live panel: ImageNets of "x": ImageNet's Infrastructural Impact (Live panel)
Spotlight talk: Learning Background Invariance Improves Generalization and Robustness in Self Supervised Learning on ImageNet and Beyond (Oral session)
Poster session B (Poster session)
Closing & awards (Workshop closing)