Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives
Authors: David T. Hoffmann, Nadine Behrmann, Juergen Gall, Thomas Brox, Mehdi Noroozi897-905
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We first study the properties of RINCE in the controlled supervised setting, looking at classification accuracy, retrieval and out-of-distribution (OOD) detection on Cifar-100. Next, we show that RINCE leads to significant improvements on the large scale dataset Image Net-100... Last, we showcase exemplary with unsupervised video representation learning that RINCE can be used in an unsupervised setting. |
| Researcher Affiliation | Collaboration | 1Bosch Center for Artificial Intelligence 2University of Freiburg 3University of Bonn |
| Pseudocode | No | No structured pseudocode or algorithm blocks were found in the paper. |
| Open Source Code | Yes | 5) Code is available at1. The Sup. Mat. can be found in (Hoffmann et al. 2022). 1https://github.com/boschresearch/rince |
| Open Datasets | Yes | Datasets. Cifar-100 (Krizhevsky, Hinton et al. 2009) ... Tiny Image Net (Le and Yang 2015) ... Image Net-100 (Tian, Krishnan, and Isola 2020) ... Kinetics-400 (Kay et al. 2017) and discard the labels. Our version of the dataset consists of 234.584 training videos. We evaluate the learned representation via finetuning on UCF (Soomro, Zamir, and Shah 2012) and HMDB (Kuehne et al. 2011) |
| Dataset Splits | No | No explicit description of training/validation/test dataset splits (e.g., percentages, absolute counts, or specific split files) was found, though standard benchmark splits are implied by dataset usage. |
| Hardware Specification | No | No specific hardware details (e.g., GPU models, CPU types, memory amounts) used for running experiments were mentioned in the paper. |
| Software Dependencies | No | No specific software dependencies with version numbers (e.g., libraries, frameworks, or compilers with their versions) were explicitly listed in the paper. |
| Experiment Setup | No | More implementation details in the Sup. Mat. |