LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions

• URL: http://arxiv.org/abs/2411.16760v1
• Date: Sun, 24 Nov 2024 15:02:52 GMT
• Title: LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributions
• Authors: Faridoun Mehri, Mahdieh Soleymani Baghshah, Mohammad Taher Pilehvar,
• Abstract summary: gradient-based explanations struggle with Transformers, and how can we improve them? We identify flow imbalances in Transformers that violate FullGrad-completeness, a critical property for attribution gradient that CNNs naturally possess. We introduce LibraGrad -- a theoretically grounded post-hoc approach that corrects gradient imbalances through pruning and scaling of backward paths.
• Score: 17.88069510398486
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Why do gradient-based explanations struggle with Transformers, and how can we improve them? We identify gradient flow imbalances in Transformers that violate FullGrad-completeness, a critical property for attribution faithfulness that CNNs naturally possess. To address this issue, we introduce LibraGrad -- a theoretically grounded post-hoc approach that corrects gradient imbalances through pruning and scaling of backward paths, without changing the forward pass or adding computational overhead. We evaluate LibraGrad using three metric families: Faithfulness, which quantifies prediction changes under perturbations of the most and least relevant features; Completeness Error, which measures attribution conservation relative to model outputs; and Segmentation AP, which assesses alignment with human perception. Extensive experiments across 8 architectures, 4 model sizes, and 4 datasets show that LibraGrad universally enhances gradient-based methods, outperforming existing white-box methods -- including Transformer-specific approaches -- across all metrics. We demonstrate superior qualitative results through two complementary evaluations: precise text-prompted region highlighting on CLIP models and accurate class discrimination between co-occurring animals on ImageNet-finetuned models -- two settings on which existing methods often struggle. LibraGrad is effective even on the attention-free MLP-Mixer architecture, indicating potential for extension to other modern architectures. Our code is freely available at https://github.com/NightMachinery/LibraGrad.

Related papers

• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)
• GradMetaNet: An Equivariant Architecture for Learning on Gradients [18.350495600116712]
  We introduce GradMetaNet, a novel architecture for learning on gradients.<n>We prove results for GradMetaNet, and show that previous approaches cannot approximate natural gradient-based functions.<n>We then demonstrate GradMetaNet's effectiveness on a diverse set of gradient-based tasks.
  arXiv  Detail & Related papers  (2025-07-02T12:22:39Z)
• Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models [66.1595537904019]
  Large language models (LLMs) can act as gradient priors in a zero-shot setting. We introduce LM-GC, a novel method that integrates LLMs with arithmetic coding.
  arXiv  Detail & Related papers  (2024-09-26T13:38:33Z)
• PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization [35.922096876707975]
  PACE is a generalization of PArameter-efficient fine-tuning with Consistency rEgularization. It implicitly regularizes gradients for enhanced generalization, but also implicitly aligns the fine-tuned and pre-trained models to retain knowledge. It also improves LoRA in text classification (GLUE) and mathematical reasoning.
  arXiv  Detail & Related papers  (2024-09-25T17:56:00Z)
• No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations [30.9134119244757]
  FUNGI is a method to enhance the features of transformer encoders by leveraging self-supervised gradients. Our method is simple: given any pretrained model, we first compute gradients from various self-supervised objectives for each input. The resulting features are evaluated on k-nearest neighbor classification over 11 datasets from vision, 5 from natural language processing, and 2 from audio.
  arXiv  Detail & Related papers  (2024-07-15T17:58:42Z)
• Gradient Projection For Continual Parameter-Efficient Tuning [42.800411328615894]
  We reformulate Adapter, LoRA, Prefix-tuning, and Prompt-tuning from the perspective of gradient projection. We show that the condition for the gradient can effectively resist forgetting even for large-scale models. We extensively evaluate our method with different backbones, including ViT and CLIP, on diverse datasets.
  arXiv  Detail & Related papers  (2024-05-22T06:33:48Z)
• Class Gradient Projection For Continual Learning [99.105266615448]
  Catastrophic forgetting is one of the most critical challenges in Continual Learning (CL) We propose Class Gradient Projection (CGP), which calculates the gradient subspace from individual classes rather than tasks.
  arXiv  Detail & Related papers  (2023-11-25T02:45:56Z)
• Scaling Forward Gradient With Local Losses [117.22685584919756]
  Forward learning is a biologically plausible alternative to backprop for learning deep neural networks. We show that it is possible to substantially reduce the variance of the forward gradient by applying perturbations to activations rather than weights. Our approach matches backprop on MNIST and CIFAR-10 and significantly outperforms previously proposed backprop-free algorithms on ImageNet.
  arXiv  Detail & Related papers  (2022-10-07T03:52:27Z)
• Magic ELF: Image Deraining Meets Association Learning and Transformer [63.761812092934576]
  This paper aims to unify CNN and Transformer to take advantage of their learning merits for image deraining. A novel multi-input attention module (MAM) is proposed to associate rain removal and background recovery. Our proposed method (dubbed as ELF) outperforms the state-of-the-art approach (MPRNet) by 0.25 dB on average.
  arXiv  Detail & Related papers  (2022-07-21T12:50:54Z)
• Binarizing by Classification: Is soft function really necessary? [4.329951775163721]
  We propose to tackle network binarization as a binary classification problem. We also take binarization as a lightweighting approach for pose estimation models. The proposed method enables binary networks to achieve a mAP of up to $60.6$ for the first time.
  arXiv  Detail & Related papers  (2022-05-16T02:47:41Z)
• GradViT: Gradient Inversion of Vision Transformers [83.54779732309653]
  We demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. We introduce a method, named GradViT, that optimize random noise into naturally looking images. We observe unprecedentedly high fidelity and closeness to the original (hidden) data.
  arXiv  Detail & Related papers  (2022-03-22T17:06:07Z)
• Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer [17.455782652441187]
  We propose a semi-supervised network for wide-angle portraits correction. Our network, named as Multi-Scale Swin-Unet (MS-Unet), is built upon the multi-scale swin transformer block (MSTB)
  arXiv  Detail & Related papers  (2021-09-14T09:40:25Z)
• Adapting Stepsizes by Momentumized Gradients Improves Optimization and Generalization [89.66571637204012]
  textscAdaMomentum on vision, and achieves state-the-art results consistently on other tasks including language processing. textscAdaMomentum on vision, and achieves state-the-art results consistently on other tasks including language processing. textscAdaMomentum on vision, and achieves state-the-art results consistently on other tasks including language processing.
  arXiv  Detail & Related papers  (2021-06-22T03:13:23Z)

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.