Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks

• URL: http://arxiv.org/abs/2407.12588v2
• Date: Thu, 18 Jul 2024 06:55:33 GMT
• Title: Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
• Authors: Antoni Kowalczuk, Jan Dubiński, Atiyeh Ashari Ghomi, Yi Sui, George Stein, Jiapeng Wu, Jesse C. Cresswell, Franziska Boenisch, Adam Dziedzic,
• Abstract summary: We present a comprehensive empirical evaluation of the adversarial robustness of self-supervised vision encoders across multiple downstream tasks. Our attacks operate in the encoder embedding space and at the downstream task output level. Since the purpose of a foundation model is to cater to multiple applications at once, our findings reveal the need to enhance encoder robustness more broadly.
• Score: 9.207022068713867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been explored for a single task, namely image classification. The vulnerability of other common vision tasks, such as semantic segmentation and depth estimation, remains largely unknown. We present a comprehensive empirical evaluation of the adversarial robustness of self-supervised vision encoders across multiple downstream tasks. Our attacks operate in the encoder embedding space and at the downstream task output level. In both cases, current state-of-the-art adversarial fine-tuning techniques tested only for classification significantly degrade clean and robust performance on other tasks. Since the purpose of a foundation model is to cater to multiple applications at once, our findings reveal the need to enhance encoder robustness more broadly. Our code is available at ${github.com/layer6ai-labs/ssl-robustness}$.

Related papers

• A Multitask Deep Learning Model for Classification and Regression of Hyperspectral Images: Application to the large-scale dataset [44.94304541427113]
  We propose a multitask deep learning model to perform multiple classification and regression tasks simultaneously on hyperspectral images. We validated our approach on a large hyperspectral dataset called TAIGA. A comprehensive qualitative and quantitative analysis of the results shows that the proposed method significantly outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-23T11:14:54Z)
• Plain-Det: A Plain Multi-Dataset Object Detector [22.848784430833835]
  Plain-Det offers flexibility to accommodate new datasets, in performance across diverse datasets, and training efficiency. We conduct extensive experiments on 13 downstream datasets and Plain-Det demonstrates strong generalization capability.
  arXiv  Detail & Related papers  (2024-07-14T05:18:06Z)
• GLID: Pre-training a Generalist Encoder-Decoder Vision Model [36.242095346942556]
  We propose a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. GLID allows the pre-trained generalist encoder-decoder to be fine-tuned on various vision tasks with minimal task-specific architecture modifications. GLID achieves competitive performance on various vision tasks, including object detection, image segmentation, pose estimation, and depth estimation.
  arXiv  Detail & Related papers  (2024-04-11T09:43:07Z)
• Can the Query-based Object Detector Be Designed with Fewer Stages? [15.726619371300558]
  We propose a novel model called GOLO, which follows a two-stage decoding paradigm. Compared to other mainstream query-based models with multi-stage decoders, our model employs fewer decoder stages while still achieving considerable performance.
  arXiv  Detail & Related papers  (2023-09-28T09:58:52Z)
• Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models [80.23791222509644]
  Inconsistent AI models are considered brittle and untrustworthy by human users. We find that state-of-the-art vision-language models suffer from a surprisingly high degree of inconsistent behavior across tasks. We propose a rank correlation-based auxiliary training objective, computed over large automatically created cross-task contrast sets.
  arXiv  Detail & Related papers  (2023-03-28T16:57:12Z)
• Fine-Grained ImageNet Classification in the Wild [0.0]
  Robustness tests can uncover several vulnerabilities and biases which go unnoticed during the typical model evaluation stage. In our work, we perform fine-grained classification on closely related categories, which are identified with the help of hierarchical knowledge.
  arXiv  Detail & Related papers  (2023-03-04T12:25:07Z)
• Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks [86.66733026149892]
  We propose Uni-Perceiver v2, which is the first generalist model capable of handling major large-scale vision and vision-gnostic tasks. Specifically, images are encoded as general region proposals, while texts are encoded via a Transformer-based language model. Uni-Perceiver v2 achieves competitive performance on a broad range of vision and vision-language tasks.
  arXiv  Detail & Related papers  (2022-11-17T18:59:52Z)
• MulT: An End-to-End Multitask Learning Transformer [66.52419626048115]
  We propose an end-to-end Multitask Learning Transformer framework, named MulT, to simultaneously learn multiple high-level vision tasks. Our framework encodes the input image into a shared representation and makes predictions for each vision task using task-specific transformer-based decoder heads.
  arXiv  Detail & Related papers  (2022-05-17T13:03:18Z)
• A Deeper Look into DeepCap [96.67706102518238]
  We propose a novel deep learning approach for monocular dense human performance capture. Our method is trained in a weakly supervised manner based on multi-view supervision. Our approach outperforms the state of the art in terms of quality and robustness.
  arXiv  Detail & Related papers  (2021-11-20T11:34:33Z)
• FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking [92.48078680697311]
  Multi-object tracking (MOT) is an important problem in computer vision. We present a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet. The approach achieves high accuracy for both detection and tracking.
  arXiv  Detail & Related papers  (2020-04-04T08:18:00Z)
• DeepCap: Monocular Human Performance Capture Using Weak Supervision [106.50649929342576]
  We propose a novel deep learning approach for monocular dense human performance capture. Our method is trained in a weakly supervised manner based on multi-view supervision. Our approach outperforms the state of the art in terms of quality and robustness.
  arXiv  Detail & Related papers  (2020-03-18T16:39:56Z)

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.