Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection

• URL: http://arxiv.org/abs/2503.17080v1
• Date: Fri, 21 Mar 2025 12:10:38 GMT
• Title: Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection
• Authors: Gensheng Pei, Tao Chen, Yujia Wang, Xinhao Cai, Xiangbo Shu, Tianfei Zhou, Yazhou Yao,
• Abstract summary: We present a concise yet effective approach called Patch Generation-to-Selection to enhance CLIP's training efficiency.<n>Our approach, CLIP-PGS, sets new state-of-the-art results in zero-shot classification and retrieval tasks.
• Score: 54.21851618853518
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The CLIP model has demonstrated significant advancements in aligning visual and language modalities through large-scale pre-training on image-text pairs, enabling strong zero-shot classification and retrieval capabilities on various domains. However, CLIP's training remains computationally intensive, with high demands on both data processing and memory. To address these challenges, recent masking strategies have emerged, focusing on the selective removal of image patches to improve training efficiency. Although effective, these methods often compromise key semantic information, resulting in suboptimal alignment between visual features and text descriptions. In this work, we present a concise yet effective approach called Patch Generation-to-Selection to enhance CLIP's training efficiency while preserving critical semantic content. Our method introduces a gradual masking process in which a small set of candidate patches is first pre-selected as potential mask regions. Then, we apply Sobel edge detection across the entire image to generate an edge mask that prioritizes the retention of the primary object areas. Finally, similarity scores between the candidate mask patches and their neighboring patches are computed, with optimal transport normalization refining the selection process to ensure a balanced similarity matrix. Our approach, CLIP-PGS, sets new state-of-the-art results in zero-shot classification and retrieval tasks, achieving superior performance in robustness evaluation and language compositionality benchmarks.

Related papers

• Globality Strikes Back: Rethinking the Global Knowledge of CLIP in Training-Free Open-Vocabulary Semantic Segmentation [5.3499687969383345]
  Recent works modify CLIP to perform semantic segmentation in a training-free manner (TF-OVSS)<n>With their modifications, the ability of CLIP to aggregate global context information is largely weakened.<n>We propose a new method named GCLIP, which mines the beneficial global knowledge of CLIP to facilitate the TF-OVSS task.
  arXiv  Detail & Related papers  (2025-02-05T03:37:50Z)
• Adapting Vision-Language Model with Fine-grained Semantics for Open-Vocabulary Segmentation [42.020470627552136]
  Open-vocabulary segmentation is primarily bottlenecked by mask classification, not mask generation.<n>We propose a novel Fine-grained Semantic Adaptation (FISA) method to address this limitation.<n>FISA enhances the extracted visual features with fine-grained semantic awareness by explicitly integrating this crucial semantic information early in the visual encoding process.
  arXiv  Detail & Related papers  (2024-09-24T17:50:28Z)
• Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation [21.719002349607308]
  Weakly Supervised Semantic dataset (WSSS) using only image-level labels has gained significant attention due to its cost-effectiveness.<n>Recent methods based on Vision Transformers (ViT) have demonstrated superior capabilities in generating reliable pseudo-labels.<n>We introduce a novel ViT-based WSSS method named textit Patch Contrast ( APC) that significantly enhances patch embedding learning.
  arXiv  Detail & Related papers  (2024-07-15T12:10:05Z)
• Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification [54.96876797812238]
  We present a novel CrOss-moDal nEighbor Representation(CODER) based on the distance structure between images and their neighbor texts. The key to construct a high-quality CODER lies in how to create a vast amount of high-quality and diverse texts to match with images. Experiment results across various datasets and models confirm CODER's effectiveness.
  arXiv  Detail & Related papers  (2024-04-27T02:04:36Z)
• Variance-insensitive and Target-preserving Mask Refinement for Interactive Image Segmentation [68.16510297109872]
  Point-based interactive image segmentation can ease the burden of mask annotation in applications such as semantic segmentation and image editing. We introduce a novel method, Variance-Insensitive and Target-Preserving Mask Refinement to enhance segmentation quality with fewer user inputs. Experiments on GrabCut, Berkeley, SBD, and DAVIS datasets demonstrate our method's state-of-the-art performance in interactive image segmentation.
  arXiv  Detail & Related papers  (2023-12-22T02:31:31Z)
• MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation [110.09800389100599]
  We propose MixReorg, a novel and straightforward pre-training paradigm for semantic segmentation. Our approach involves generating fine-grained patch-text pairs data by mixing image patches while preserving the correspondence between patches and text. With MixReorg as a mask learner, conventional text-supervised semantic segmentation models can achieve highly generalizable pixel-semantic alignment ability.
  arXiv  Detail & Related papers  (2023-08-09T09:35:16Z)
• Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training [55.12082817901671]
  We propose a new self-supervised pre-training approach, named Masked and Permuted Vision Transformer (MaPeT)<n>MaPeT employs autoregressive and permuted predictions to capture intra-patch dependencies.<n>Our results demonstrate that MaPeT achieves competitive performance on ImageNet, compared to baselines and competitors under the same model setting.
  arXiv  Detail & Related papers  (2023-06-12T18:12:19Z)
• No Token Left Behind: Explainability-Aided Image Classification and Generation [79.4957965474334]
  We present a novel explainability-based approach, which adds a loss term to ensure that CLIP focuses on all relevant semantic parts of the input. Our method yields an improvement in the recognition rate, without additional training or fine-tuning.
  arXiv  Detail & Related papers  (2022-04-11T07:16:39Z)
• Robust Cross-Modal Representation Learning with Progressive Self-Distillation [7.676408770854477]
  The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets. We introduce a novel training framework based on cross-modal contrastive learning that uses progressive self-distillation and soft image-text alignments to more efficiently learn robust representations from noisy data.
  arXiv  Detail & Related papers  (2022-04-10T03:28:18Z)
• A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model [61.58071099082296]
  It is unclear how to make zero-shot recognition working well on broader vision problems, such as object detection and semantic segmentation. In this paper, we target for zero-shot semantic segmentation, by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. Our experimental results show that this simple framework surpasses previous state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2021-12-29T18:56:18Z)

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.