NoFADE: Analyzing Diminishing Returns on CO2 Investment

• URL: http://arxiv.org/abs/2111.14059v1
• Date: Sun, 28 Nov 2021 05:48:48 GMT
• Title: NoFADE: Analyzing Diminishing Returns on CO2 Investment
• Authors: Andre Fu and Justin Tran and Andy Xie and Jonathan Spraggett and Elisa Ding and Chang-Won Lee and Kanav Singla and Mahdi S. Hosseini and Konstantinos N. Plataniotis
• Abstract summary: NoFADE is a novel entropy-based metric to quantify model--dataset--complexity relationships. NoFADE allows the CV community to compare models and datasets on a similar basis, establishing an agnostic platform.
• Score: 25.539221177092575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Climate change continues to be a pressing issue that currently affects society at-large. It is important that we as a society, including the Computer Vision (CV) community take steps to limit our impact on the environment. In this paper, we (a) analyze the effect of diminishing returns on CV methods, and (b) propose a \textit{``NoFADE''}: a novel entropy-based metric to quantify model--dataset--complexity relationships. We show that some CV tasks are reaching saturation, while others are almost fully saturated. In this light, NoFADE allows the CV community to compare models and datasets on a similar basis, establishing an agnostic platform.

Related papers

• RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability [3.301728339780329]
  We propose REpresentation Shift QUantifying Estimator (RESQUE), a predictive quantifier to estimate the retraining cost of a model. RESQUE provides a single concise index for an estimate of resources required for retraining the model. Our results validate that RESQUE is an effective indicator in terms of epochs, gradient norms, changes of parameter magnitude, energy, and carbon emissions.
  arXiv  Detail & Related papers  (2024-12-20T02:55:07Z)
• Efficient Aspect-Based Summarization of Climate Change Reports with Small Language Models [0.0]
  We release a new dataset for Aspect-Based Summarization (ABS) of Climate Change reports. We employ different Large Language Models (LLMs) and so-called Small Language Models (SLMs) to tackle this problem in an unsupervised way. Considering the problem at hand, we also show how SLMs are not significantly worse for the problem while leading to reduced carbon footprint.
  arXiv  Detail & Related papers  (2024-11-21T16:28:32Z)
• VHELM: A Holistic Evaluation of Vision Language Models [75.88987277686914]
  We present the Holistic Evaluation of Vision Language Models (VHELM) VHELM aggregates various datasets to cover one or more of the 9 aspects: visual perception, knowledge, reasoning, bias, fairness, multilinguality, robustness, toxicity, and safety. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast.
  arXiv  Detail & Related papers  (2024-10-09T17:46:34Z)
• RelVAE: Generative Pretraining for few-shot Visual Relationship Detection [2.2230760534775915]
  We present the first pretraining method for few-shot predicate classification that does not require any annotated relations. We construct few-shot training splits and show quantitative experiments on VG200 and VRD datasets.
  arXiv  Detail & Related papers  (2023-11-27T19:08:08Z)
• Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks [65.21536453075275]
  We focus on the summarization task and investigate the membership inference (MI) attack. We exploit text similarity and the model's resistance to document modifications as potential MI signals. We discuss several safeguards for training summarization models to protect against MI attacks and discuss the inherent trade-off between privacy and utility.
  arXiv  Detail & Related papers  (2023-10-20T05:44:39Z)
• CorrFL: Correlation-Based Neural Network Architecture for Unavailability Concerns in a Heterogeneous IoT Environment [3.9414768019101682]
  The Federated Learning (FL) paradigm faces several challenges that limit its application in real-world environments. These challenges include the local models' architecture heterogeneity and the unavailability of distributed Internet of Things (IoT) nodes due to connectivity problems. This paper proposes the Correlation-based FL (CorrFL) approach influenced by the representational learning field to address this problem.
  arXiv  Detail & Related papers  (2023-07-22T19:23:06Z)
• Scaling Laws Do Not Scale [54.72120385955072]
  Recent work has argued that as the size of a dataset increases, the performance of a model trained on that dataset will increase. We argue that this scaling law relationship depends on metrics used to measure performance that may not correspond with how different groups of people perceive the quality of models' output. Different communities may also have values in tension with each other, leading to difficult, potentially irreconcilable choices about metrics used for model evaluations.
  arXiv  Detail & Related papers  (2023-07-05T15:32:21Z)
• OOD-CV-v2: An extended Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Images [59.51657161097337]
  OOD-CV-v2 is a benchmark dataset that includes out-of-distribution examples of 10 object categories in terms of pose, shape, texture, context and the weather conditions. In addition to this novel dataset, we contribute extensive experiments using popular baseline methods.
  arXiv  Detail & Related papers  (2023-04-17T20:39:25Z)
• Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning [112.69497636932955]
  Federated learning aims to train models across different clients without the sharing of data for privacy considerations. We study how data heterogeneity affects the representations of the globally aggregated models. We propose sc FedDecorr, a novel method that can effectively mitigate dimensional collapse in federated learning.
  arXiv  Detail & Related papers  (2022-10-01T09:04:17Z)
• Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future [73.03458424369657]
  In real-time forecasting in public health, data collection is a non-trivial and demanding task. 'Backfill' phenomenon and its effect on model performance has been barely studied in the prior literature. We formulate a novel problem and neural framework Back2Future that aims to refine a given model's predictions in real-time.
  arXiv  Detail & Related papers  (2021-06-08T14:48:20Z)
• Reconsidering CO2 emissions from Computer Vision [39.04604349338802]
  We analyze the total cost of CO2 emissions by breaking it into (1) the architecture creation cost and (2) the life-time evaluation cost. We show that over time, these costs are non-negligible and are having a direct impact on our future. We propose adding "enforcement" as a pillar of ethical AI and provide some recommendations for how architecture designers and broader CV community can curb the climate crisis.
  arXiv  Detail & Related papers  (2021-04-18T04:01:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.