Search Results for author:
Found 10 papers, 9 papers with code
CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
Interestingly, data and architectural improvements seem to mitigate the negative impact of data balancing on performance; e. g. applying M4 to SigLIP-B/16 with data quality filters improves COCO image-to-text retrieval @5 from 86% (without data balancing) to 87% and ImageNet 0-shot classification from 77% to 77. 5%!
A Self-Supervised Descriptor for Image Copy Detection
We adapt this method to the copy detection task by changing the architecture and training objective, including a pooling operator from the instance matching literature, and adapting contrastive learning to augmentations that combine images.
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images.
Ranked #1 on
Copy Detection
on Copydays strong subset
(using extra training data)
Fairness Indicators for Systematic Assessments of Visual Feature Extractors
Systematic diagnosis of fairness, harms, and biases of computer vision systems is an important step towards building socially responsible systems.
Self-supervised Pretraining of Visual Features in the Wild
Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods.
Ranked #6 on
Image Classification
on Places205
Self-Supervised Image Classification
Self-Supervised Learning
+1
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements much.
Ranked #9 on
Image Classification
on OmniBenchmark
Scaling and Benchmarking Self-Supervised Visual Representation Learning
Self-supervised learning aims to learn representations from the data itself without explicit manual supervision.
Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
Deep learning models with convolutional and recurrent networks are now ubiquitous and analyze massive amounts of audio, image, video, text and graph data, with applications in automatic translation, speech-to-text, scene understanding, ranking user preferences, ad placement, etc.
Focal Loss for Dense Object Detection
Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
Ranked #3 on
Region Proposal
on COCO test-dev
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
To achieve this result, we adopt a hyper-parameter-free linear scaling rule for adjusting learning rates as a function of minibatch size and develop a new warmup scheme that overcomes optimization challenges early in training.
