Alternatives and similar repositories for last-layer-retraining

Users that are interested in last-layer-retraining are comparing it to the libraries listed below

• BigML-CS-UCLA / SpuCo
  SpuCo is a Python package developed to further research to address spurious correlations.
  ☆25Updated last year
• adaminsky / compositional_concepts
  Code for the CCE algorithm proposed in "Towards Compositionality in Concept Learning" at ICML 2024.
  ☆17Updated last year
• kdariina / CLIP-not-BoW-unimodally
  Code for "CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally"
  ☆18Updated 11 months ago
• YanNeu / spurious_imagenet
  Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet
  ☆32Updated 2 years ago
• ExplainableML / WaffleCLIP
  Official repository for the ICCV 2023 paper: "Waffling around for Performance: Visual Classification with Random Words and Broad Concepts…
  ☆61Updated 2 years ago
• facebookresearch / Whac-A-Mole
  Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"
  ☆50Updated last year
• brendel-group / clip-ood
  Official code for the paper "Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?" (ICLR 2024)
  ☆10Updated last year
• alinlab / b2t
  Bias-to-Text: Debiasing Unknown Visual Biases through Language Interpretation
  ☆32Updated 2 years ago
• Trustworthy-ML-Lab / Linear-Explanations
  [ICML 24] A novel automated neuron explanation framework that can accurately describe poly-semantic concepts in deep neural networks
  ☆14Updated 8 months ago
• naver-ai / dawin
  [ICLR 2025] Official PyTorch implementation of "DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation"
  ☆26Updated 6 months ago
• piotr-teterwak / erm_plusplus
  ☆17Updated last year
• izmailovpavel / spurious_feature_learning
  ☆47Updated 3 years ago
• Wuyxin / DISC
  (ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation
  ☆43Updated 2 months ago
• BatsResearch / ex2
  If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions
  ☆17Updated last year
• ExplainableML / fomo_in_flux
  Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]
  ☆61Updated last year
• PolinaKirichenko / deep_feature_reweighting
  ☆111Updated 2 years ago
• i-gao / targeted-augs
  Code for paper "Out-of-Domain Robustness via Targeted Augmentations"
  ☆14Updated 2 years ago
• andrijazz / ash
  Code release for paper Extremely Simple Activation Shaping for Out-of-Distribution Detection
  ☆55Updated last year
• aengusl / spawrious
  ☆29Updated last year
• anniesch / surgical-finetuning
  Code for "Surgical Fine-Tuning Improves Adaptation to Distribution Shifts" published at ICLR 2023
  ☆29Updated 2 years ago
• Mattdl / ContinualEvaluation
  [Spotlight ICLR 2023 paper] Continual evaluation for lifelong learning with neural networks, identifying the stability gap.
  ☆30Updated 2 years ago
• paulgavrikov / vlm_shapebias
  Official code for "Can We Talk Models Into Seeing the World Differently?" (ICLR 2025).
  ☆27Updated 11 months ago
• deeplearning-wisc / poem
  PyTorch implementation of POEM (Out-of-distribution detection with posterior sampling), ICML 2022
  ☆28Updated 2 years ago
• abonte / protopdebug
  Implementation of Concept-level Debugging of Part-Prototype Networks
  ☆12Updated 2 years ago
• aliasgharkhani / Masktune
  ☆29Updated 3 years ago
• yossigandelsman / second_order_lens
  Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"
  ☆42Updated last year
• mlfoundations / clip_quality_not_quantity
  ☆29Updated 3 years ago
• lapisrocks / DiscreteAdversarialDistillation
  [NeurIPS 2023] Official repository for "Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models"
  ☆12Updated last year
• k1rezaei / Text-to-concept
  ☆35Updated last year
• shengliu66 / LC
  Official Implementation of Avoiding spurious correlations via logit correction
  ☆17Updated 2 years ago