Rank-N-Contrast: Learning Continuous Representations for Regression

Authors: Kaiwen Zha, Peng Cao, Jeany Son, Yuzhe Yang, Dina Katabi

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments using five real-world regression datasets that span computer vision, human-computer interaction, and healthcare verify that RNC achieves state-of-the-art performance, highlighting its intriguing properties including better data efficiency, robustness to spurious targets and data corruptions, and generalization to distribution shifts. Code is available at: https://github.com/kaiwenzha/Rank-N-Contrast.
Researcher Affiliation Academia Kaiwen Zha1, Peng Cao1, Jeany Son2 Yuzhe Yang1 Dina Katabi1 1MIT CSAIL 2GIST
Pseudocode No The paper provides mathematical formulations of the Rank-N-Contrast Loss (LRNC) but does not include a pseudocode block or a clearly labeled algorithm.
Open Source Code Yes Code is available at: https://github.com/kaiwenzha/Rank-N-Contrast.
Open Datasets Yes Age DB (Age) [32, 44] is a dataset for predicting age from face images, containing 16,488 in-the-wild images of celebrities and the corresponding age labels. TUAB (Brain-Age) [34, 11] aims for brain-age estimation from EEG resting-state signals, with 1,385 21-channel EEG signals sampled at 200Hz from individuals with age from 0 to 95. MPIIFace Gaze (Gaze Direction) [51, 52] contains 213,659 face images collected from 15 participants during natural everyday laptop use. Sky Finder (Temperature) [31, 7] contains 35,417 images captured by 44 outdoor webcam cameras for in-the-wild temperature prediction. IMDB-WIKI (Age) [36, 44] is a large dataset for predicting age from face images, which contains 523,051 celebrity images and the corresponding age labels.
Dataset Splits Yes Age DB... It is split into a 12,208-image training set, a 2140-image validation set, and a 2140-image test set. MPIIFace Gaze... We subsample and split it into a 33,000-image training set, a 6,000-image validation set, and a 6,000image test set with no overlapping participants. Sky Finder... It is split into a 28,373-image training set, a 3,522-image validation set, and a 3,522-image test set. IMDB-WIKI... We subsample the dataset to create a variable size training set, and keep the validation set and test set unchanged with 11,022 images in each.
Hardware Specification Yes All experiments are trained using 8 NVIDIA TITAN RTX GPUs.
Software Dependencies No The paper mentions using "SGD optimizer" and "cosine learning rate annealing" but does not specify software or library versions (e.g., PyTorch, TensorFlow versions).
Experiment Setup Yes The batch size is set to 256. For one-stage methods and encoder training of two-stage methods, we select the best learning rates and weight decays for each dataset by grid search, with a grid of learning rates from {0.01, 0.05, 0.1, 0.2, 0.5, 1.0} and weight decays from {10 6, 10 5, 10 4, 10 3}. For the predictor training of two-stage methods, we adopt the same search setting as above except for adding no weight decay to the search choices of weight decays. For temperature parameter τ, we search from {0.1, 0.2, 0.5, 1.0, 2.0, 5.0} and select the best, which is 2.0. We train all one-stage methods and the encoder of two-stage methods for 400 epochs, and the linear regressor of two-stage methods for 100 epochs.